Skip to content

generic-automation-and-it/smooth-ai-stockanalysis / .agents/skills/manage-rule-system

manage-rule-system

Verified

Convention for creating, updating, or modifying rule files in .agents/rules/. Use when adding, editing, or restructuring rule files to ensure compatibility across Claude Code, GitHub Copilot, Cursor, and OpenAI Codex.

FileKindSize
AGENTS.mdmarkdown1.1 KB
SKILL.mdskill md5.8 KB
agents/openai.yamlconfig293 B
scripts/inject-context.shexecutablescript1.0 KB
# manage-rule-system — AGENTS.md

## TL;DR

Convention skill for `.agents/rules/` files, injected on demand by `scripts/inject-context.sh` (UserPromptSubmit hook) rather than loaded every session — the injection is deduped once per session.

## Key Behaviors

- `inject-context.sh` dedupes via a tracker file in `/tmp` keyed by session id (falls back through `CLAUDE_SESSION_ID` → Codex/Copilot ids → `$PPID`). On id-less runners every prompt re-injects the SKILL.md — if that shows up, fix the session-id chain, not the hook matcher.
- Rule files physically live in `.github/instructions/` (real dir for Copilot's hosted agent); `.agents/rules` is a symlink. Any path advice this skill gives must keep that direction — pointing the symlink the other way breaks github.com-side Copilot.
- The same rule tree is now distributable to other repos via `ai-template-sync --rules-only`; structural changes here (folder layout, frontmatter contract) propagate to consumers on their next pinned sync.

## Changelog

| Date | Change | Ref |
|:-----|:-------|:----|
| 2026-06-12 | Initial version. | |
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall