{"version":"mdrss-catalog-feed/2","domain":{"slug":"ai-agents","label":"AI Agents","description":"Coding agents, agent frameworks, tools, prompting, evaluation, safety, and autonomous workflows.","categories":["coding-agents","agent-frameworks","mcp-and-tools","prompting","agent-design-and-orchestration","mcp-tooling-and-context","prompting-and-agent-evaluation","multi-agent-systems","agent-memory-and-context","agent-tools-and-function-calling","agent-safety-and-governance","agent-observability","agent-evaluation-and-benchmarks","autonomous-workflows","agent-security"]},"total":57,"page":1,"page_size":50,"total_pages":2,"has_next":true,"has_previous":false,"filters":{"domain":"ai-agents","category":"coding-agents"},"feeds":[{"slug":"ai-agents-and-prompting","url":"https://mdrss.com/s/ai-agents-and-prompting"},{"slug":"ai-search-geo-and-seo","url":"https://mdrss.com/s/ai-search-geo-and-seo"}],"urls":{"html":"https://mdrss.com/catalog/ai-agents?category=coding-agents","rss":"https://mdrss.com/catalog/ai-agents/rss.xml?category=coding-agents","json":"https://mdrss.com/catalog/ai-agents/feed.json?category=coding-agents","markdown":"https://mdrss.com/catalog/ai-agents/index.md?category=coding-agents"},"updated_at":"2026-08-04T12:22:38.168Z","items":[{"id":2366,"title":"Claude Design System Prompt","annotation":"Reverse-engineered system prompt of Claude Design from Anthropic. A system prompt and skill library that turns an LLM into an opinionated, accessibility-aware, AI-slop-resistant design collaborator.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:00.584Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/2366","permalink_url":"https://mdrss.com/m/2366","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/2366/2366.md","file_url":"https://mdrss.com/api/v1/cards/2366/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/2366/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/2366/embed","edit_url":"https://mdrss.com/cards/2366/edit","legacy_url":"https://mdrss.com/s/ai-agents/trystan-sa-claude-design-system-prompt-trystan-sa-claude-design-system-prompt-re"},{"id":2324,"title":"metaswarm","annotation":"A self-improving multi-agent orchestration framework for Claude Code, Gemini CLI, and Codex CLI. Coordinate 18 specialized AI agents and 13 orchestration skills through a complete software development lifecycle, from issue to merged PR, with recursive orchestration, parallel review gates, and a git-native knowledge base.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:06.594Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/2324","permalink_url":"https://mdrss.com/m/2324","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/2324/2324.md","file_url":"https://mdrss.com/api/v1/cards/2324/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/2324/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/2324/embed","edit_url":"https://mdrss.com/cards/2324/edit","legacy_url":"https://mdrss.com/s/ai-agents/dsifry-metaswarm-dsifry-metaswarm-readme"},{"id":2228,"title":"Claude Hooks","annotation":"A collection of security and utility hooks for Claude Code. Hooks allow you to extend Claude Code's behavior by running custom scripts at key points during execution.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:06.594Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/2228","permalink_url":"https://mdrss.com/m/2228","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/2228/2228.md","file_url":"https://mdrss.com/api/v1/cards/2228/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/2228/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/2228/embed","edit_url":"https://mdrss.com/cards/2228/edit","legacy_url":"https://mdrss.com/s/ai-agents/lasso-security-claude-hooks-lasso-security-claude-hooks-readme"},{"id":2204,"title":"Resume Skills for Claude Code","annotation":"A collection of AI agent skills focused on resume optimization, job applications, and career development. Built for job seekers, career changers, and professionals who want Claude Code to help with resume writing, ATS optimization, interview prep, and strategic job search.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:26.961Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/2204","permalink_url":"https://mdrss.com/m/2204","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/2204/2204.md","file_url":"https://mdrss.com/api/v1/cards/2204/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/2204/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/2204/embed","edit_url":"https://mdrss.com/cards/2204/edit","legacy_url":"https://mdrss.com/s/ai-agents/paramchoudhary-resumeskills-paramchoudhary-resumeskills-readme"},{"id":1714,"title":"Econ Writing Skill","annotation":"An Agent Skill that transforms AI assistants into expert economics paper writers, synthesizing best practices from 50+ authoritative guides by Nobel laureates, Clark Medal winners, and leading economists. --- Econ Writing Skill is an open-source Agent Skill that gives AI coding assistants deep knowledge of how to write economics papers.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:26.961Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/1714","permalink_url":"https://mdrss.com/m/1714","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/1714/1714.md","file_url":"https://mdrss.com/api/v1/cards/1714/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/1714/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/1714/embed","edit_url":"https://mdrss.com/cards/1714/edit","legacy_url":"https://mdrss.com/s/ai-agents/hanlulong-econ-writing-skill-hanlulong-econ-writing-skill-readme"},{"id":1495,"title":"Quick start (30 giây)","annotation":"ai-business-skills Fullstack marketing skills cho AI agent — 63 skills bilingual (VN + Global). Vietnamese-first + Global (US/EU/SEA/LATAM) | Over Powers Agency --- Windows: Test ngay trong Claude Code: → Skill 00-ke-hoach-mkt tự kích hoạt, output file .md chi tiết với benchmark VN 2025-2026, KPI 3 kịch bản, budget allocation, weekly timeline, risk matrix.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:00.584Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/1495","permalink_url":"https://mdrss.com/m/1495","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/1495/1495.md","file_url":"https://mdrss.com/api/v1/cards/1495/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/1495/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/1495/embed","edit_url":"https://mdrss.com/cards/1495/edit","legacy_url":"https://mdrss.com/s/ai-agents/minhnv0807-ai-business-skills-minhnv0807-ai-business-skills-readme"},{"id":1313,"title":"SocratiCode","annotation":"The open-source codebase context engine: give any AI instant automated knowledge of your entire codebase (and infrastructure) — at scale, zero configuration, fully private, completely free. Kindly sponsored by Altaire Limited One thing, done well: deep codebase intelligence — zero setup, no bloat, fully automatic.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:05.306Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/1313","permalink_url":"https://mdrss.com/m/1313","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/1313/1313.md","file_url":"https://mdrss.com/api/v1/cards/1313/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/1313/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/1313/embed","edit_url":"https://mdrss.com/cards/1313/edit","legacy_url":"https://mdrss.com/s/ai-agents/giancarloerra-socraticode-giancarloerra-socraticode-readme"},{"id":1169,"title":"Highlights","annotation":"CowAgent is lightweight, easy to deploy, and built to extend. Plug in any major LLM provider and run it 24/7 on a personal computer or server, across the web and all major IM platforms.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:06.594Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/1169","permalink_url":"https://mdrss.com/m/1169","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/1169/1169.md","file_url":"https://mdrss.com/api/v1/cards/1169/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/1169/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/1169/embed","edit_url":"https://mdrss.com/cards/1169/edit","legacy_url":"https://mdrss.com/s/ai-agents/zhayujie-cowagent-zhayujie-cowagent-readme"},{"id":1074,"title":"Prompt Architect","annotation":"Transform vague prompts into expert-level, structured prompts using 31 frameworks across 7 intent categories. Works with Claude Code, ChatGPT, Gemini CLI, Cursor, GitHub Copilot, Windsurf, OpenAI Codex, and 30+ Agent Skills compatible tools.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:06.594Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/1074","permalink_url":"https://mdrss.com/m/1074","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/1074/1074.md","file_url":"https://mdrss.com/api/v1/cards/1074/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/1074/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/1074/embed","edit_url":"https://mdrss.com/cards/1074/edit","legacy_url":"https://mdrss.com/s/ai-agents/ckelsoe-prompt-architect-ckelsoe-prompt-architect-readme"},{"id":1030,"title":"Pm Skills","annotation":"PM-Skills A curated library of 68 best-practice, plug-and-play product management skills covering the complete product lifecycle - plus templates, workflows, and 200+ real-world sample outputs that set the quality bar. The catalog is frozen at the v2.9.2 build; subsequent v2.9.x patches do not change the catalog.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:16:59.230Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/1030","permalink_url":"https://mdrss.com/m/1030","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/1030/1030.md","file_url":"https://mdrss.com/api/v1/cards/1030/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/1030/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/1030/embed","edit_url":"https://mdrss.com/cards/1030/edit","legacy_url":"https://mdrss.com/s/ai-agents/product-on-purpose-pm-skills-product-on-purpose-pm-skills-readme"},{"id":982,"title":"ArcKit: The Enterprise Architecture Governance Harness","annotation":"Build better enterprise architecture through structured strategy, design, delivery, and assurance workflows. The 13 community plugins (arckit-uae, arckit-fr, arckit-ca, arckit-eu, arckit-at, arckit-au, arckit-au-energy, arckit-us, arckit-uk-finance, arckit-uk-nhs, arckit-uk-gcloud, arckit-togaf-adm, arckit-agent-architecture) require the arckit core plugin.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:28.388Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/982","permalink_url":"https://mdrss.com/m/982","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/982/982.md","file_url":"https://mdrss.com/api/v1/cards/982/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/982/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/982/embed","edit_url":"https://mdrss.com/cards/982/edit","legacy_url":"https://mdrss.com/s/ai-agents/tractorjuice-arc-kit-tractorjuice-arc-kit-readme"},{"id":941,"title":"GPT Image2 Skill","annotation":"GPT Image 2 Prompt Gallery + Agentic Skill + CLI OpenAI GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI — curated, copy-paste prompts and runnable examples for skill-capable agents. It includes reusable AI image prompts for research paper figures, posters, UI mockups, game HUDs, anime / manga, photography, typography, maps, tattoo design, and reference-image editing workflows.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:02.193Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/941","permalink_url":"https://mdrss.com/m/941","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/941/941.md","file_url":"https://mdrss.com/api/v1/cards/941/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/941/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/941/embed","edit_url":"https://mdrss.com/cards/941/edit","legacy_url":"https://mdrss.com/s/ai-agents/wuyoscar-gpt-image2-skill-wuyoscar-gpt-image2-skill-readme"},{"id":934,"title":"Zero-Dependency Brainstorm Server Implementation Plan","annotation":"Goal: Replace the brainstorm server's vendored nodemodules with a single zero-dependency server.js using Node built-ins. Architecture: Single file with WebSocket protocol (RFC 6455 text frames), HTTP server (http module), and file watching (fs.watch).","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:29.513Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/934","permalink_url":"https://mdrss.com/m/934","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/934/934.md","file_url":"https://mdrss.com/api/v1/cards/934/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/934/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/934/embed","edit_url":"https://mdrss.com/cards/934/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-plans-2026-03-11-zero-dep-bra"},{"id":933,"title":"Document Review System Implementation Plan","annotation":"Goal: Add spec and plan document review loops to the brainstorming and writing-plans skills. Architecture: Create reviewer prompt templates in each skill directory.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:06.594Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/933","permalink_url":"https://mdrss.com/m/933","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/933/933.md","file_url":"https://mdrss.com/api/v1/cards/933/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/933/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/933/embed","edit_url":"https://mdrss.com/cards/933/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-plans-2026-01-22-document-rev"},{"id":928,"title":"Writing Plans","annotation":"--- name: writing-plans description: Use when you have a spec or requirements for a multi-step task, before touching code --- Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:31.039Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/928","permalink_url":"https://mdrss.com/m/928","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/928/928.md","file_url":"https://mdrss.com/api/v1/cards/928/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/928/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/928/embed","edit_url":"https://mdrss.com/cards/928/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-skills-writing-plans-skill"},{"id":927,"title":"Code Review Reception","annotation":"NEVER: INSTEAD: Example: your human partner's rule: \"External feedback - be skeptical, but check carefully\" your human partner's rule: \"You and reviewer both report to me. If we don't need this feature, don't add it.\" Push back when: How to push back: If you're uncomfortable pushing back out loud: Name that tension, then tell your partner about the issue you've seen.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:26.961Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/927","permalink_url":"https://mdrss.com/m/927","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/927/927.md","file_url":"https://mdrss.com/api/v1/cards/927/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/927/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/927/embed","edit_url":"https://mdrss.com/cards/927/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-skills-receiving-code-review-skill"},{"id":918,"title":"peon-ping","annotation":"English | 한국어 | 中文 | 日本語 Game character voice lines + visual overlay notifications when your AI coding agent needs attention — or let the agent pick its own sound via MCP. AI coding agents don't notify you when they finish or need permission.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:29.513Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/918","permalink_url":"https://mdrss.com/m/918","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/918/918.md","file_url":"https://mdrss.com/api/v1/cards/918/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/918/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/918/embed","edit_url":"https://mdrss.com/cards/918/edit","legacy_url":"https://mdrss.com/s/ai-agents/peonping-peon-ping-peonping-peon-ping-readme"},{"id":912,"title":"Writing Good Tests","annotation":"Load this reference when: writing or changing tests, adding mocks, or adding cleanup/helper methods for tests. Two principles govern everything here: Strict TDD produces both naturally: a test written first and watched failing against real code has already proven it can fail, and only earns a mock when the real dependency proves slow or external.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:28.388Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/912","permalink_url":"https://mdrss.com/m/912","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/912/912.md","file_url":"https://mdrss.com/api/v1/cards/912/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/912/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/912/embed","edit_url":"https://mdrss.com/cards/912/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-skills-test-driven-development-writing-good-te"},{"id":911,"title":"Persuasion Principles for Skill Design","annotation":"LLMs respond to the same persuasion principles as humans. Understanding this psychology helps you design more effective skills - not to manipulate, but to ensure critical practices are followed even under pressure.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:29.513Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/911","permalink_url":"https://mdrss.com/m/911","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/911/911.md","file_url":"https://mdrss.com/api/v1/cards/911/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/911/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/911/embed","edit_url":"https://mdrss.com/cards/911/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-skills-writing-skills-persuasion-principles"},{"id":907,"title":"Finishing a Development Branch","annotation":"--- name: finishing-a-development-branch description: Use when implementation is complete, all tests pass, and you need to decide how to integrate the work --- Core principle: Verify tests → Detect environment → Present options → Execute choice → Clean up. Announce at start: \"I'm using the finishing-a-development-branch skill to complete this work.\" Run the project's full test suite (npm test / cargo test / pytest / go test ./...).","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:03.599Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/907","permalink_url":"https://mdrss.com/m/907","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/907/907.md","file_url":"https://mdrss.com/api/v1/cards/907/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/907/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/907/embed","edit_url":"https://mdrss.com/cards/907/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-skills-finishing-a-development-branch-skill"},{"id":906,"title":"Visual Brainstorming Refactor Implementation Plan","annotation":"Goal: Refactor visual brainstorming from blocking TUI feedback model to non-blocking \"Browser Displays, Terminal Commands\" architecture. Architecture: Browser becomes an interactive display; terminal stays the conversation channel.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:06.594Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/906","permalink_url":"https://mdrss.com/m/906","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/906/906.md","file_url":"https://mdrss.com/api/v1/cards/906/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/906/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/906/embed","edit_url":"https://mdrss.com/cards/906/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-plans-2026-02-19-visual-brain"},{"id":896,"title":"Codex App Compatibility Implementation Plan","annotation":"Goal: Make using-git-worktrees, finishing-a-development-branch, and related skills work in the Codex App's sandboxed worktree environment without breaking existing behavior. Architecture: Read-only environment detection (git-dir vs git-common-dir) at the start of two skills.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:03.599Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/896","permalink_url":"https://mdrss.com/m/896","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/896/896.md","file_url":"https://mdrss.com/api/v1/cards/896/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/896/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/896/embed","edit_url":"https://mdrss.com/cards/896/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-plans-2026-03-23-codex-app-co"},{"id":890,"title":"Agentmemory","annotation":"Built on iii engine Persistent memory for Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI, Hermes, OpenClaw, pi, OpenCode, and any MCP client. English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Español | Türkçe | Русский | हिन्दी | Português | Français | Deutsch The gist extends Karpathy's LLM Wiki pattern with confidence scoring, lifecycle, knowledge graphs, and hybrid search: agentmemory is the implementation.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:05.306Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/890","permalink_url":"https://mdrss.com/m/890","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/890/890.md","file_url":"https://mdrss.com/api/v1/cards/890/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/890/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/890/embed","edit_url":"https://mdrss.com/cards/890/edit","legacy_url":"https://mdrss.com/s/ai-agents/rohitg00-agentmemory-rohitg00-agentmemory-readme"},{"id":889,"title":"OpenCode Support Design","annotation":"Date: 2025-11-22 Author: Bot & Jesse Status: Design Complete, Awaiting Implementation Add full superpowers support for OpenCode.ai using a native OpenCode plugin architecture that shares core functionality with the existing Codex implementation. OpenCode.ai is a coding agent similar to Claude Code and Codex.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:29.513Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/889","permalink_url":"https://mdrss.com/m/889","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/889/889.md","file_url":"https://mdrss.com/api/v1/cards/889/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/889/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/889/embed","edit_url":"https://mdrss.com/cards/889/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-plans-2025-11-22-opencode-support-design"},{"id":884,"title":"Cross-Platform Polyglot Hooks for Claude Code","annotation":"Claude Code plugins need hooks that work on Windows, macOS, and Linux. This document describes the single generic dispatcher pattern used in hooks/run-hook.cmd.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:29.513Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/884","permalink_url":"https://mdrss.com/m/884","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/884/884.md","file_url":"https://mdrss.com/api/v1/cards/884/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/884/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/884/embed","edit_url":"https://mdrss.com/cards/884/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-windows-polyglot-hooks"},{"id":880,"title":"Systematic Debugging","annotation":"--- name: systematic-debugging description: Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes --- Core principle: ALWAYS find root cause before attempting fixes. Violating the letter of this process is violating the spirit of debugging.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:28.388Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/880","permalink_url":"https://mdrss.com/m/880","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/880/880.md","file_url":"https://mdrss.com/api/v1/cards/880/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/880/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/880/embed","edit_url":"https://mdrss.com/cards/880/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-skills-systematic-debugging-skill"},{"id":879,"title":"Visual Companion Auth Hardening Design","annotation":"Date: 2026-06-10 Status: Draft for Drew review Fix the security and reliability gaps found in PR #1720's brainstorming visual companion without changing the companion's core workflow or adding runtime dependencies. The fixes must be test-first and must leave clear automated evidence for: The companion serves agent-generated local UI for a single brainstorming session.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:28.388Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/879","permalink_url":"https://mdrss.com/m/879","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/879/879.md","file_url":"https://mdrss.com/api/v1/cards/879/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/879/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/879/embed","edit_url":"https://mdrss.com/cards/879/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-specs-2026-06-10-visual-compa"},{"id":878,"title":"Awesome Agent Skills","annotation":"A collection of official Agent Skills from leading development teams and the community. Unlike many bulk-generated skill repositories, this collection focuses on real-world Agent Skills created and used by actual engineering teams, not mass AI‑generated stuff.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"dataset","version":1,"snapshot_at":"2026-08-04T12:17:05.306Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/878","permalink_url":"https://mdrss.com/m/878","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/878/878.md","file_url":"https://mdrss.com/api/v1/cards/878/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/878/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/878/embed","edit_url":"https://mdrss.com/cards/878/edit","legacy_url":"https://mdrss.com/s/ai-agents/voltagent-awesome-agent-skills-voltagent-awesome-agent-skills-readme"},{"id":870,"title":"SDD Fix-Loop Redesign — Design Spec","annotation":"Status: Approved design (brainstormed with Jesse 2026-07-15); implementation plan to follow. Objective: make the subagent-driven-development skill's review-fix loop convergent and autonomous, and make the document readable, without rewriting its eval-tuned language.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"spec","version":1,"snapshot_at":"2026-08-04T12:17:02.193Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/870","permalink_url":"https://mdrss.com/m/870","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/870/870.md","file_url":"https://mdrss.com/api/v1/cards/870/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/870/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/870/embed","edit_url":"https://mdrss.com/cards/870/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-specs-2026-07-15-sdd-fix-loop"},{"id":869,"title":"Positive-Instruction Redesign of Skill Guidance — Design Spec","annotation":"Status: Proposed (follow-up to the 2026-06-09 SDD review-dispatch work; separate PR per the one-problem-per-PR rule) Driver: Measured evidence (2026-06-10) that some negative instructions in skill prose backfire, while others work — and that the difference is predictable. Micro-tests on 2026-06-10 (opus, 5 reps per phrasing, programmatic scoring; harness described below) measured how guidance phrasing changes what a controller composes: |---|---|---| The doctrine (use this to","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"spec","version":1,"snapshot_at":"2026-08-04T12:17:03.599Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/869","permalink_url":"https://mdrss.com/m/869","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/869/869.md","file_url":"https://mdrss.com/api/v1/cards/869/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/869/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/869/embed","edit_url":"https://mdrss.com/cards/869/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-specs-2026-06-10-positive-ins"},{"id":864,"title":"Understand Anything","annotation":"Understand Anything Turn any codebase, knowledge base, or docs into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:02.193Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/864","permalink_url":"https://mdrss.com/m/864","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/864/864.md","file_url":"https://mdrss.com/api/v1/cards/864/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/864/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/864/embed","edit_url":"https://mdrss.com/cards/864/edit","legacy_url":"https://mdrss.com/s/ai-agents/egonex-ai-understand-anything-egonex-ai-understand-anything-readme"},{"id":863,"title":"Visual Companion Auth Hardening Implementation Plan","annotation":"Goal: Harden the brainstorming visual companion auth and reconnect flow while preserving trusted same-origin screen JavaScript and future vendored UI libraries. Architecture: Keyed root loads become a bootstrap step that sets the cookie, stores the key in tab-scoped sessionStorage, and navigates to a bare / screen URL.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:26.961Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/863","permalink_url":"https://mdrss.com/m/863","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/863/863.md","file_url":"https://mdrss.com/api/v1/cards/863/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/863/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/863/embed","edit_url":"https://mdrss.com/cards/863/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-plans-2026-06-10-visual-compa"},{"id":858,"title":"SDD Task-Scoped Review Dispatch Implementation Plan","annotation":"Goal: Scope SDD's per-task reviews to the task (diff-first reading, justified broadening, no redundant test runs) while final branch review stays broad. skills/requesting-code-review/ is deliberately untouched.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:02.193Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/858","permalink_url":"https://mdrss.com/m/858","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/858/858.md","file_url":"https://mdrss.com/api/v1/cards/858/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/858/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/858/embed","edit_url":"https://mdrss.com/cards/858/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-plans-2026-06-09-sdd-task-sco"},{"id":849,"title":"Visual Brainstorming Refactor: Browser Displays, Terminal Commands","annotation":"Date: 2026-02-19 Status: Approved Scope: lib/brainstorm-server/, skills/brainstorming/visual-companion.md, tests/brainstorm-server/ During visual brainstorming, Claude runs wait-for-feedback.sh as a background task and blocks on TaskOutput(block=true, timeout=600s). This seizes the TUI entirely — the user cannot type to Claude while visual brainstorming is running.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:31.039Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/849","permalink_url":"https://mdrss.com/m/849","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/849/849.md","file_url":"https://mdrss.com/api/v1/cards/849/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/849/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/849/embed","edit_url":"https://mdrss.com/cards/849/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-specs-2026-02-19-visual-brain"},{"id":848,"title":"Visual Companion Final Hardening Fixup Implementation Plan","annotation":"Goal: Finish PR #1720's final hardening fixup with test-first changes, clean rebase state, and reviewer-ready evidence. Spec: docs/superpowers/specs/2026-06-11-visual-companion-final-hardening-fixup-design.md Architecture: Keep the companion zero-dependency and local-first.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:03.599Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/848","permalink_url":"https://mdrss.com/m/848","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/848/848.md","file_url":"https://mdrss.com/api/v1/cards/848/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/848/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/848/embed","edit_url":"https://mdrss.com/cards/848/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-plans-2026-06-11-visual-compa"},{"id":839,"title":"Visual Companion Guide","annotation":"Browser-based visual brainstorming companion for showing mockups, diagrams, and options. The test: would the user understand this better by seeing it than reading it?","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:00.584Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/839","permalink_url":"https://mdrss.com/m/839","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/839/839.md","file_url":"https://mdrss.com/api/v1/cards/839/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/839/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/839/embed","edit_url":"https://mdrss.com/cards/839/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-skills-brainstorming-visual-companion"},{"id":838,"title":"Codex App Compatibility: Worktree and Finishing Skill Adaptation","annotation":"Make superpowers skills work in the Codex App's sandboxed worktree environment without breaking existing Claude Code or Codex CLI behavior. Ticket: PRI-823 The Codex App runs agents inside git worktrees it manages — detached HEAD, located under $CODEXHOME/worktrees/, with a Seatbelt sandbox that blocks git checkout -b, git push, and network access.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:05.306Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/838","permalink_url":"https://mdrss.com/m/838","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/838/838.md","file_url":"https://mdrss.com/api/v1/cards/838/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/838/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/838/embed","edit_url":"https://mdrss.com/cards/838/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-specs-2026-03-23-codex-app-co"},{"id":832,"title":"Visual Companion Final Hardening Fixup Design","annotation":"Date: 2026-06-11 Status: Draft for Drew review Finish the PR #1720 visual companion hardening pass so the branch is ready for Jesse review with clean security behavior, deterministic tests, and a PR diff that contains only the companion work. This is a fixup on top of the existing auth hardening design.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:28.388Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/832","permalink_url":"https://mdrss.com/m/832","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/832/832.md","file_url":"https://mdrss.com/api/v1/cards/832/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/832/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/832/embed","edit_url":"https://mdrss.com/cards/832/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-specs-2026-06-11-visual-compa"},{"id":828,"title":"Caveman","annotation":"why use many token when few do trick Make your AI coding agent talk like a caveman. 65% fewer output tokens on prose, 8.5% on agentic coding runs .","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:26.961Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/828","permalink_url":"https://mdrss.com/m/828","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/828/828.md","file_url":"https://mdrss.com/api/v1/cards/828/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/828/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/828/embed","edit_url":"https://mdrss.com/cards/828/edit","legacy_url":"https://mdrss.com/s/ai-agents/juliusbrussee-caveman-juliusbrussee-caveman-readme"},{"id":822,"title":"Strict-Cost SDD — Design Spec","annotation":"Status: Proposed experiment ladder (not implementation). Each rung ships only with its gate evidence; abort any rung whose gates fail.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"spec","version":1,"snapshot_at":"2026-08-04T12:17:02.193Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/822","permalink_url":"https://mdrss.com/m/822","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/822/822.md","file_url":"https://mdrss.com/api/v1/cards/822/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/822/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/822/embed","edit_url":"https://mdrss.com/cards/822/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-specs-2026-06-10-strict-cost"},{"id":821,"title":"SDD plan-scoped workspace — eval results","annotation":"with maintainer sign-off after the RED baseline did not reproduce blind stale-ledger adoption. 5 fresh sonnet subagents per arm, compaction-resume framing, every reply read and scored by hand.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:05.306Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/821","permalink_url":"https://mdrss.com/m/821","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/821/821.md","file_url":"https://mdrss.com/api/v1/cards/821/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/821/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/821/embed","edit_url":"https://mdrss.com/cards/821/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-specs-2026-07-06-sdd-plan-sco"},{"id":817,"title":"Superpowers","annotation":"Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them. Give your agent Superpowers: Claude Code, Antigravity, Codex App, Codex CLI, Cursor, Factory Droid, Gemini CLI, GitHub Copilot CLI, Kimi Code, OpenCode, Pi.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:03.599Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/817","permalink_url":"https://mdrss.com/m/817","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/817/817.md","file_url":"https://mdrss.com/api/v1/cards/817/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/817/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/817/embed","edit_url":"https://mdrss.com/cards/817/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-readme"},{"id":816,"title":"Testing Skills With Subagents","annotation":"Load this reference when: creating or editing skills, before deployment, to verify they work under pressure and resist rationalization. Testing skills is just TDD applied to process documentation.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:00.584Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/816","permalink_url":"https://mdrss.com/m/816","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/816/816.md","file_url":"https://mdrss.com/api/v1/cards/816/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/816/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/816/embed","edit_url":"https://mdrss.com/cards/816/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-skills-writing-skills-testing-skills-with-suba"},{"id":813,"title":"OpenCode Support Implementation Plan","annotation":"Goal: Add full superpowers support for OpenCode.ai with a native JavaScript plugin that shares core functionality with the existing Codex implementation. Architecture: Extract common skill discovery/parsing logic into lib/skills-core.js, refactor Codex to use it, then build OpenCode plugin using their native plugin API with custom tools and session hooks.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:26.961Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/813","permalink_url":"https://mdrss.com/m/813","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/813/813.md","file_url":"https://mdrss.com/api/v1/cards/813/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/813/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/813/embed","edit_url":"https://mdrss.com/cards/813/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-plans-2025-11-22-opencode-support-impleme"},{"id":812,"title":"Worktree Rototill Implementation Plan","annotation":"Goal: Make superpowers defer to native harness worktree systems when available, fall back to manual git worktrees when not, and fix three known finishing bugs. Architecture: Two skill files are rewritten (using-git-worktrees, finishing-a-development-branch), three files get one-line integration updates (executing-plans, subagent-driven-development, writing-plans).","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:00.584Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/812","permalink_url":"https://mdrss.com/m/812","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/812/812.md","file_url":"https://mdrss.com/api/v1/cards/812/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/812/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/812/embed","edit_url":"https://mdrss.com/cards/812/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-plans-2026-04-06-worktree-rot"},{"id":807,"title":"SDD Task-Scoped Review Dispatch","annotation":"Make subagent-driven-development's per-task reviews cheaper and faster without weakening them, by scoping per-task review prompts to the task and stopping redundant work — while final branch review stays broad. Per-task code quality reviewers in SDD routinely do branch-review-scale work on single-task diffs.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:29.513Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/807","permalink_url":"https://mdrss.com/m/807","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/807/807.md","file_url":"https://mdrss.com/api/v1/cards/807/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/807/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/807/embed","edit_url":"https://mdrss.com/cards/807/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-specs-2026-06-09-sdd-task-sco"},{"id":805,"title":"Ponytail","annotation":"~54% less code (up to 94%) · ~20% cheaper · ~27% faster · 100% safe Measured on real Claude Code sessions editing a real open-source repo (FastAPI + React), against the same agent with no skill. ~54% is the mean across 12 feature tasks (Haiku 4.5, n=4); it reaches 94% where an agent over-builds (a date picker) and is near zero where the code is already minimal.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:02.193Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/805","permalink_url":"https://mdrss.com/m/805","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/805/805.md","file_url":"https://mdrss.com/api/v1/cards/805/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/805/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/805/embed","edit_url":"https://mdrss.com/cards/805/edit","legacy_url":"https://mdrss.com/s/ai-agents/dietrichgebert-ponytail-dietrichgebert-ponytail-readme"},{"id":802,"title":"Subagent-Driven Development","annotation":"--- name: subagent-driven-development description: Use when executing implementation plans with independent tasks in the current session --- Execute plan by dispatching a fresh implementer subagent per task, a task review (spec compliance + code quality) after each, and a broad whole-branch review at the end. Why subagents: You delegate tasks to specialized agents with isolated context.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:05.306Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/802","permalink_url":"https://mdrss.com/m/802","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/802/802.md","file_url":"https://mdrss.com/api/v1/cards/802/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/802/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/802/embed","edit_url":"https://mdrss.com/cards/802/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-skills-subagent-driven-development-skill"},{"id":801,"title":"Worktree Rototill: Detect-and-Defer","annotation":"Date: 2026-04-06 Status: Draft Ticket: PRI-974 Subsumes: PRI-823 (Codex App compatibility) Superpowers is opinionated about worktree management — specific paths (.worktrees/ ), specific commands (git worktree add), specific cleanup (git worktree remove). Meanwhile, Claude Code, Codex App, Gemini CLI, and Cursor all provide native worktree support with their own paths, lifecycle management, and cleanup.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"guide","version":1,"snapshot_at":"2026-08-04T12:17:00.584Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/801","permalink_url":"https://mdrss.com/m/801","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/801/801.md","file_url":"https://mdrss.com/api/v1/cards/801/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/801/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/801/embed","edit_url":"https://mdrss.com/cards/801/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-specs-2026-04-06-worktree-rot"},{"id":800,"title":"Visual Brainstorming Companion — Issue & Change Catalog","annotation":"We are implementing these ourselves; the referenced community PRs are evidence and reference material, not code we intend to merge. A single place that captures every open issue and PR touching the visual brainstorming companion (the local server in skills/brainstorming/scripts/), distilled to the underlying problem and the change we'd make.","feed":"ai-agents","semantic_path":"ai-agents:coding-agents","content_type":"reference","version":1,"snapshot_at":"2026-08-04T12:17:03.599Z","publisher":"mdrss-github-collector","publisher_url":"https://mdrss.com/mdrss-github-collector","card_url":"https://mdrss.com/ai-agents/coding-agents/800","permalink_url":"https://mdrss.com/m/800","thread_url":"https://mdrss.com/s/ai-agents","markdown_url":"https://mdrss.com/ai-agents/coding-agents/800/800.md","file_url":"https://mdrss.com/api/v1/cards/800/file","raw_url":"https://mdrss.com/ai-agents/coding-agents/800/raw","embed_url":"https://mdrss.com/ai-agents/coding-agents/800/embed","edit_url":"https://mdrss.com/cards/800/edit","legacy_url":"https://mdrss.com/s/ai-agents/obra-superpowers-obra-superpowers-docs-superpowers-plans-2026-06-09-visual-compa"}]}