Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/littlebearapps/contextdocs/claude-mdgit clone --depth 1 https://github.com/littlebearapps/contextdocsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01152 | $0.01152 |
| Opus 5 | $0.00576 | $0.00576 |
| Sonnet 5 | $0.00230 | $0.00230 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
contextdocs CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ContextDocs
Canonical description (use this in all listings and submissions):
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.
Pure Markdown Claude Code plugin — no JavaScript, no Python, no build step, no runtime dependencies. Signal Gate filtering, Context Guard hooks, and 0-100 health scoring.
Commands
- Token budget test:
bash tests/check-token-budgets.sh - llms.txt validation:
bash tests/validate-llms-txt.sh - Spell check:
typos(config:_typos.toml, Australian English) - Frontmatter lint:
python3 tests/validate-frontmatter.py
Conventions
- Australian English: realise, colour, behaviour, licence (noun), license (verb)
- Conventional Commits:
feat:,fix:,docs:,chore:— release-please automates versioning - Line budgets: CLAUDE.md bridge <80, AGENTS.md <120, other bridge files <60
Architecture
- AGENTS-first generation:
AGENTS.mdis the canonical shared context for commands, conventions, constraints, and security notes - Thin bridges:
CLAUDE.md,.cursor/rules/agents.mdc, optional Copilot instructions,.clinerules/agents.md,.windsurfrules, andGEMINI.mdshould add only tool-specific behaviour - Modern formats: Modern Cursor uses
.cursor/rules/*.mdcwith frontmatter (description / globs / alwaysApply); modern Cline uses the.clinerules/directory with optionalpaths:per-file frontmatter. Legacy.cursorrulesand flat.clinerulesare preserved only when already present - Optional bridges:
.github/copilot-instructions.mdis optional — Copilot's coding agent loads AGENTS.md natively (since Aug 2025); only emit when adding tool-specific scoping - Compatibility bridges:
.windsurfrulesandGEMINI.mdremain generated for now for tool compatibility
When Modifying
- Add a skill: Create
.claude/skills/<name>/SKILL.md+commands/<name>.md, update README.md, AGENTS.md, llms.txt, and AGENTS-first generation guidance if shared output behaviour changed - Add a command: Create
commands/<name>.mdwith YAML frontmatter, update README.md, AGENTS.md, llms.txt - Add an agent: Create
.claude/agents/<name>.mdwith frontmatter, update AGENTS.md, llms.txt, context-guard SKILL.md - Change quality standards: Edit
.claude/rules/context-quality.md— propagates automatically - Change shared conventions: Update
AGENTS.mdfirst, then only the bridge docs whose tool-specific notes change - Bump version: Handled by release-please from conventional commit messages
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 59 lines · 1,152 tokens per session scan A 0507be1a7c9d
contextdocs CLAUDE.md is an instructions file published in the GitHub repository littlebearapps/contextdocs (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,152 tokens to every session, about $0.0058 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vibe-check AGENTS.md
Instructions for benavlabs/vibe-check, covering security rules, secrets, database, authentication and authorization and input and output.
rust-faf-mcp AGENTS.md
Instructions for Wolfe-Jam/rust-faf-mcp, covering agents.md — rust-faf-mcp, setup & build, run the tests, where things live and architecture (load-bearing).
conforme AGENTS.md
Instructions for maxgfr/conforme, covering project instructions, claude.md, project overview, build & test and architecture.
conforme GEMINI.md
Instructions for maxgfr/conforme, covering claude.md, project overview, build & test, architecture and keeping docs in sync.
ai-agent-instruction-modules AGENTS.md
Instructions for tablackburn/ai-agent-instruction-modules, covering ai agent instructions, instructions for ai agents, instruction applicability matrix, available instruction files and quick reference.
conforme copilot-instructions.md
Instructions for maxgfr/conforme, covering claude.md, project overview, build & test, architecture and keeping docs in sync.