Borrowing it
Nothing to install: this file belongs to yeomyeonggeori/blueclaw. 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/yeomyeonggeori/blueclaw/main/AGENTS.mdgit clone --depth 1 https://github.com/yeomyeonggeori/blueclawWrote 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/yeomyeonggeori/blueclaw/agents-md)<a href="https://agentmods.dev/instructions/yeomyeonggeori/blueclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/yeomyeonggeori/blueclaw/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/yeomyeonggeori/blueclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/yeomyeonggeori/blueclaw/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 | $0.03134 | $0.03134 |
| Opus 5.5 | $0.01254 | $0.01254 |
| Sonnet 5.5 | $0.00627 | $0.00627 |
| Haiku 4.5 | $0.00313 | $0.00313 |
Grade A, and why
blueclaw 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 29d 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 — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
These are the conventions this codebase holds itself to. Apply them to new code, and apply them to code you touch wherever that does not break consistency with its surroundings.
Core Principles
- Readability is the highest priority - code should be self-explanatory
- Functional style - prefer pure functions, avoid side effects
- Efficiency - no redundant operations
- Simplicity - minimal code that solves the problem
Single Source of Truth
- A shared vocabulary or contract (emoji names, enum options, capability names, component lists) consumed by more than one role, package, or service is defined exactly once; every consumer derives from that definition. Hand-maintained parallel copies are a defect: they drift (one list gains a value the other never sees) and every addition requires touching N places.
- When a consumer lives in another language and cannot import the
definition, add a conformance test that reads the canonical source and
fails on drift, instead of keeping a second hand-edited copy
(
chatd/tests/buzz-adapter.test.tsreads.dependency/blueprotocol/agentcontract/reaction_emoji.go). - On discovering duplicated sources of truth, merge them as part of the change that touched them; do not extend a duplicate.
Working on this repository
Nothing lands on main by direct push. Branch, open a pull request, let the
check run, merge.
Branch names
<type>/<subject-in-kebab-case> — the type is the same word the commit will
carry, and the subject says what changes, not what you did to it.
feat/acp-context-injection
fix/approval-resume-after-restart
docs/tui-screenshots
refactor/turn-runner-split
test/completion-gate-evidence
chore/gofmt
ci/skip-docs-only-runs
Branch off main, rebase rather than merge when main moves under you, and
delete the branch once the pull request is merged.
Commit messages
<type>: <what changes, imperative, lowercase, no trailing period>
<why it changes: the problem the reader would otherwise have to reconstruct.
Wrap at 72 columns. Say what you deliberately did not do.>
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.
- 29d ago Changed · -1 tokens per session 38050c0469de
- 2mo ago First seen · 356 lines · 3,135 tokens per session scan A 2871eec408af
blueclaw AGENTS.md is an instructions file published in the GitHub repository yeomyeonggeori/blueclaw (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,134 tokens to every session, about $0.0125 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 2026-08-31.
blueclaw AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blueclaw AGENTS.mdyeomyeonggeori/blueclaw | Instructions file | 5 | yesterday | Apache-2.0 | A | 3,134 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |