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/legendtkl/agents-md-polish/agents-mdgit clone --depth 1 https://github.com/legendtkl/agents-md-polishWrote 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/legendtkl/agents-md-polish/agents-md)<a href="https://agentmods.dev/instructions/legendtkl/agents-md-polish/agents-md"><img src="https://agentmods.dev/badge/instructions/legendtkl/agents-md-polish/agents-md.svg" alt="Measured on agentmods" 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 | $0.00512 | $0.00512 |
| Opus 5 | $0.00256 | $0.00256 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
agents-md-polish 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 5d 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.
What it actually says
AGENTS.md
Invariants
- No runtime npm dependencies. v0.1 is built from Node built-ins only;
adding a dep needs a separate justification PR. Why: keeps install
footprint tiny and removes the supply-chain surface for a tool that
writes into your
.claude/and.agents/directories. - Audit thresholds live in
lib/audit.jsRULES(not inline in rule functions). New rules add a key there with cited rationale. - Templates ship in
lib/templates/and are copied verbatim at install time, with{{version}}substitution. Don't add other template variables — keep the format trivial.
Project map
- CLI entry:
bin/agents-md-polish.js - Command dispatch:
lib/cli.js - Install logic:
lib/init.js - Lint rules:
lib/audit.js - Asset inventory:
lib/doctor.js - Tool adapters (claude, codex):
lib/tools.js - Generated-by marker handling:
lib/marker.js - Skill + starter templates:
lib/templates/ - Tests:
test/*.test.js(zero-depnode:test)
Commands
- Test:
npm test - Self-audit:
npm run self-audit - Run CLI locally:
node bin/agents-md-polish.js <args>
Verification matrix
| Change scope | Required checks |
|---|---|
lib/ or bin/ |
npm test |
lib/templates/ |
npm test && npm run self-audit |
| Adding a tool adapter | also extend test/tools.test.js |
| Adding an audit rule | also extend test/audit.test.js and update README rule table |
Done definition
-
npm testpasses -
npm run self-auditpasses - Working tree clean
- Commit message explains why
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.
- 5d ago First seen · 56 lines · 512 tokens per session scan A b930230a33e7
agents-md-polish AGENTS.md is an instructions file published in the GitHub repository legendtkl/agents-md-polish (4 stars, last pushed 3mo ago), licensed MIT. It adds 512 tokens to every session, about $0.0026 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.