littlebearappslittlebearapps/contextdocs/SKILL.md

contextdocs

Skill5 starsChanged 6 months agoMITView on GitHub

Your AI agent maintains its own context files — a Claude Code plugin with an AGENTS-first model that covers Codex, Copilot, Cursor, Gemini, and 3 more tools. Signal Gate filtering, Context Guard hooks, health scoring, and MEMORY.md promotion.

In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- ai-contextSkill
- context-guardSkill
- context-verifySkill

The file

Create a free account to mount

Files

SKILL.md

ContextDocs — AI Context File Management

Overview

ContextDocs is a pure Markdown Claude Code plugin that generates, maintains, and audits AGENTS-first AI IDE context files for 8 tools. AGENTS.md carries the shared project conventions, and every generated bridge file follows the Signal Gate principle — only what agents cannot discover on their own — keeping context lean and effective.

3 skills, 3 slash commands, 2 quality rules, 6 opt-in hooks, 13 verification checks. 100% Markdown, zero runtime dependencies, MIT licensed.

When to Use

Starting a new project and need canonical AGENTS.md plus bridge files for multiple tools
Existing context files have drifted out of date with your codebase
CLAUDE.md or other bridge files are bloated with content that belongs in AGENTS.md
You want to promote patterns from MEMORY.md into CLAUDE.md
Need to score context file quality for CI/CD enforcement

Instructions

Install the plugin:

/plugin marketplace add littlebearapps/lba-plugins
/plugin install contextdocs@lba-plugins

Navigate to any project repository
Run commands:
- /contextdocs:ai-context init — Bootstrap canonical AGENTS.md plus all needed bridges
- /contextdocs:ai-context update — Patch only what drifted
- /contextdocs:ai-context promote — Move MEMORY.md patterns to CLAUDE.md
- /contextdocs:ai-context audit — Check for staleness and drift
- /contextdocs:context-guard install — Install freshness hooks (Claude Code only)
- /contextdocs:context-verify — Score context file health (0–100)

Output Format

Each generated file is written directly to the repository. AGENTS.md is the shared source of truth; bridge files add only tool-specific guidance.

File	Role	Budget
AGENTS.md	Canonical shared context	<120 lines
CLAUDE.md	Claude bridge	<80 lines
.cursorrules	Cursor bridge	<60 lines
.github/copilot-instructions.md	Copilot bridge	<60 lines
.windsurfrules	Windsurf compatibility bridge	<60 lines
.clinerules	Cline bridge	<60 lines
GEMINI.md	Gemini compatibility bridge	<60 lines

Notes

Works with Claude Code and OpenCode natively; generated files support 8 AI tools total
Signal Gate filtering excludes directory listings, file trees, and architecture overviews
Context Guard hooks are Claude Code only (opt-in)
For public-facing documentation (README, CHANGELOG, ROADMAP), see PitchDocs

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free