Borrowing it
Nothing to install: this file belongs to crittylabs/critty. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/crittylabs/critty/main/AGENTS.mdgit clone --depth 1 https://github.com/crittylabs/crittyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/crittylabs/critty/agents-md)<a href="https://agentmods.dev/instructions/crittylabs/critty/agents-md"><img src="https://agentmods.dev/badge/instructions/crittylabs/critty/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/crittylabs/critty/agents-md"><img src="https://agentmods.dev/badge/instructions/crittylabs/critty/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.01377 | $0.01377 |
| Opus 5.5 | $0.00551 | $0.00551 |
| Sonnet 5.5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
critty AGENTS.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 3d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
This file is read by coding agents such as Claude Code and Codex.
Local notes
If AGENTS.local.md exists next to this file, read it before starting work and follow it. It holds a developer's local additions, is not committed, and takes precedence over this file where they differ.
How we work
- Keep
README.mdfocused on feature benefits, installation, basic workflows and controls, and important limitations for human users. Link to bundled skills underinternal/cli/skill/and built-in help for details; update affected skills alongside CLI or workflow changes. - Keep bundled skills focused on agent workflows and CLI contracts. Document human TUI controls in built-in help and
README.md. - Update
README.mdin the release preparation commit. For major visual changes or headline features, propose recording new demos. - Research Crit's current implementation and documentation when changing the review format or workflow, and use the findings to inform specification and compatibility decisions.
- In commit messages, put key names such as
Rorctrl+vand command names in backquotes.
Changelog maintenance
Treat Unreleased as a compact description of the final user-visible differences from the latest published release. Update it as a whole, rather than adding a record for each commit or task.
Before every changelog update:
- Verify the latest published release and its tag. Compare that tag with the final changes being prepared, including in-scope uncommitted work; the previous commit is not the baseline.
- Read all of
Unreleasedand find the entries covering the affected features. Rewrite those entries to describe the final behavior, merging related additions, refinements, and fixes into one entry per user-visible change. Add a separate entry only for an independent difference from the release baseline. - Remove superseded behavior, duplicate explanations, and fixes for problems introduced and resolved after the baseline. Retain fixes for problems present in a published release, including prereleases; verify publication history before removing them.
- Check the complete section against the release comparison. Every entry must describe a remaining user-visible difference, and every such difference, including small fixes, must be covered. Keep only the wording needed to explain those differences and their important constraints.
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.
- 3d ago Changed · +15 lines · +356 tokens per session 34f8a314be0c
- 4d ago First seen · 60 lines · 1,021 tokens per session scan A 11bbf5d8731c
critty AGENTS.md is an instructions file published in the GitHub repository crittylabs/critty (88 stars, last pushed yesterday), licensed MIT. It adds 1,377 tokens to every session, about $0.0055 per session on Opus 5.5. 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 2026-10-12.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).