# #coding — MDRSS hashtag feed

> Public MDRSS cards tagged #coding.
> Canonical feed: https://mdrss.com/feeds/coding

## Cards (42)

### [Mobile security coder](https://mdrss.com/security/application-security-and-threat-modeling/901310/901310.md)

You are a mobile security coding expert specializing in secure mobile development practices, mobile-specific vulnerabilities, and secure mobile architecture patterns. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: security/application-security-and-threat-modeling · Feed: security · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Backend security coder](https://mdrss.com/security/application-security-and-threat-modeling/901197/901197.md)

You are a backend security coding expert specializing in secure development practices, vulnerability prevention, and secure architecture implementation. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: security/application-security-and-threat-modeling · Feed: security · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [AI-RULES](https://mdrss.com/ai-agents/prompting-and-agent-evaluation/901067/901067.md)

AI-RULES is a rule-aware CLI for AI-assisted coding governance. It turns project rules in Markdown into structured rule metadata, lightweight local evidence, and deterministic audit/fix prompts so AI coding agents follow your architecture, design patterns, and UI standards more c. Use it as a repeatable review, validation or hardening pass.

Classification: ai-agents/prompting-and-agent-evaluation · Feed: ai-agents · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Zero-Dependency Brainstorm Server Implementation Plan](https://mdrss.com/ai-agents/coding-agents/934/934.md)

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).

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Document Review System Implementation Plan](https://mdrss.com/ai-agents/coding-agents/933/933.md)

Goal: Add spec and plan document review loops to the brainstorming and writing-plans skills. Architecture: Create reviewer prompt templates in each skill directory.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Writing Plans](https://mdrss.com/ai-agents/coding-agents/928/928.md)

--- 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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Code Review Reception](https://mdrss.com/ai-agents/coding-agents/927/927.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Writing Good Tests](https://mdrss.com/ai-agents/coding-agents/912/912.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Persuasion Principles for Skill Design](https://mdrss.com/ai-agents/coding-agents/911/911.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Finishing a Development Branch](https://mdrss.com/ai-agents/coding-agents/907/907.md)

--- 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 ./...).

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Visual Brainstorming Refactor Implementation Plan](https://mdrss.com/ai-agents/coding-agents/906/906.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Using Git Worktrees](https://mdrss.com/software-craft/developer-tooling/902/902.md)

--- name: using-git-worktrees description: Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback --- Ensure work happens in an isolated workspace. Prefer your platform's native worktree tools.

Classification: software-craft/developer-tooling · Feed: software-craft · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Codex App Compatibility Implementation Plan](https://mdrss.com/ai-agents/coding-agents/896/896.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [OpenCode Support Design](https://mdrss.com/ai-agents/coding-agents/889/889.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Cross-Platform Polyglot Hooks for Claude Code](https://mdrss.com/ai-agents/coding-agents/884/884.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Systematic Debugging](https://mdrss.com/ai-agents/coding-agents/880/880.md)

--- 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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Visual Companion Auth Hardening Design](https://mdrss.com/ai-agents/coding-agents/879/879.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [SDD Fix-Loop Redesign — Design Spec](https://mdrss.com/ai-agents/coding-agents/870/870.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Positive-Instruction Redesign of Skill Guidance — Design Spec](https://mdrss.com/ai-agents/coding-agents/869/869.md)

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

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Test-Driven Development (TDD)](https://mdrss.com/software-craft/testing-and-quality/868/868.md)

--- name: test-driven-development description: Use when implementing any feature or bugfix, before writing implementation code --- Write the test first. Core principle: If you didn't watch the test fail, you don't know if it tests the right thing.

Classification: software-craft/testing-and-quality · Feed: software-craft · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Visual Companion Auth Hardening Implementation Plan](https://mdrss.com/ai-agents/coding-agents/863/863.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [SDD Task-Scoped Review Dispatch Implementation Plan](https://mdrss.com/ai-agents/coding-agents/858/858.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Visual Brainstorming Refactor: Browser Displays, Terminal Commands](https://mdrss.com/ai-agents/coding-agents/849/849.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Visual Companion Final Hardening Fixup Implementation Plan](https://mdrss.com/ai-agents/coding-agents/848/848.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Visual Companion Guide](https://mdrss.com/ai-agents/coding-agents/839/839.md)

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?

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Codex App Compatibility: Worktree and Finishing Skill Adaptation](https://mdrss.com/ai-agents/coding-agents/838/838.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Visual Companion Final Hardening Fixup Design](https://mdrss.com/ai-agents/coding-agents/832/832.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Strict-Cost SDD — Design Spec](https://mdrss.com/ai-agents/coding-agents/822/822.md)

Status: Proposed experiment ladder (not implementation). Each rung ships only with its gate evidence; abort any rung whose gates fail.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [SDD plan-scoped workspace — eval results](https://mdrss.com/ai-agents/coding-agents/821/821.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Superpowers](https://mdrss.com/ai-agents/coding-agents/817/817.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Testing Skills With Subagents](https://mdrss.com/ai-agents/coding-agents/816/816.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [OpenCode Support Implementation Plan](https://mdrss.com/ai-agents/coding-agents/813/813.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Worktree Rototill Implementation Plan](https://mdrss.com/ai-agents/coding-agents/812/812.md)

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).

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [SDD Task-Scoped Review Dispatch](https://mdrss.com/ai-agents/coding-agents/807/807.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Subagent-Driven Development](https://mdrss.com/ai-agents/coding-agents/802/802.md)

--- 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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Worktree Rototill: Detect-and-Defer](https://mdrss.com/ai-agents/coding-agents/801/801.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Visual Brainstorming Companion — Issue & Change Catalog](https://mdrss.com/ai-agents/coding-agents/800/800.md)

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.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Writing Skills](https://mdrss.com/ai-agents/coding-agents/796/796.md)

--- name: writing-skills description: Use when creating new skills, editing existing skills, or verifying skills work before deployment --- Writing skills IS Test-Driven Development applied to process documentation. Personal skills live in your runtime's skills directory (~/.claude/skills/ on Claude Code) — see codex-tools.md or gemini-tools.md for the path on those runtimes.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Lift drill into superpowers as evals/ — implementation plan](https://mdrss.com/ai-agents/coding-agents/785/785.md)

Goal: Move the standalone obra/drill skill-compliance benchmark into superpowers as a top-level evals/ directory, delete redundant bash tests under superpowers/tests/ after per-file subagent verification of drill scenario coverage, and update top-level docs so contributors land on the new structure. Architecture: Single PR against dev on a new branch f/evals-lift.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [SDD Plan-Scoped Workspace Implementation Plan](https://mdrss.com/ai-agents/coding-agents/774/774.md)

Goal: Make SDD's durable-progress workspace plan-scoped (.superpowers/sdd/ /) with a self-identifying ledger and end-of-plan cleanup, so a follow-up plan can never collide with a previous plan's artifacts and resumed controllers stop paying a forensic disambiguation tax. Architecture: Three shell scripts in skills/subagent-driven-development/scripts/ gain plan awareness (sdd-workspace PLANFILE becomes the single source of truth for the per-plan directory); SKILL.md's Durable

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [SDD Fix-Loop Redesign Implementation Plan](https://mdrss.com/ai-agents/coding-agents/770/770.md)

Goal: Make subagent-driven-development's review-fix loop convergent and autonomous (resume-the-implementer fix rounds, scoped re-reviews, five-round breaker, controller adjudication) and reorganize its SKILL.md by lifecycle — with quorum eval evidence. The superpowers repo (branch sdd-fix-loop-redesign, already created; spec committed) gets the skill restructure: one new prompt template, two template edits, one reference edit, and the SKILL.md rewrite whose full text is in Ta

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Porting Superpowers to a New Harness](https://mdrss.com/ai-agents/coding-agents/763/763.md)

This guide explains how to add support for a new harness — an IDE, CLI, or agent runner that isn't Claude Code — so that Superpowers skills auto-trigger there the same way they do natively. Part 1–3 explain how the system works and how to tell whether a harness can be supported at all; read these before you touch anything.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1