Skip to content

generic-automation-and-it/smooth-ai-stockanalysis / .agents/skills/context-load-agents-context

context-load-agents-context

Verified

Load ancestor AGENTS.md context for a target file. Use when Codex, Claude, Copilot, or another agent needs local domain context before reading or editing source files.

FileKindSize
AGENTS.mdmarkdown962 B
SKILL.mdskill md3.5 KB
agents/openai.yamlconfig234 B
references/design.mdmarkdown8.3 KB
scripts/load-agents-context.shexecutablescript5.9 KB
# context-load-agents-context — AGENTS.md

## TL;DR

Hook + skill wrapper around `scripts/load-agents-context.sh`; full design rationale (six LADRs, sequence diagram, transfer checklist) lives in `references/design.md` — read it before modifying the script.

## Non-Negotiables

- **The script must always exit 0.** It runs as a `PostToolUse` hook; a non-zero exit blocks the user's Read/Edit/Write. Swallow all file-operation failures.
- **Never emit files from auto-loaded rule dirs** (`.agents/rules/`, `.claude/rules/`, `.cursor/rules/`, `.github/instructions/`) — they're already in context; re-emitting doubles their token cost.

## Key Behaviors

- Session dedup canonicalises physical paths, so the same AGENTS.md reached via `.claude/...` and `.agents/...` symlinks is emitted once — breaking canonicalisation silently doubles context injection.

## 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