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/permacommons/lib.reviews/agents-mdgit clone --depth 1 https://github.com/permacommons/lib.reviewsWrote 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/permacommons/lib.reviews/agents-md)<a href="https://agentmods.dev/instructions/permacommons/lib.reviews/agents-md"><img src="https://agentmods.dev/badge/instructions/permacommons/lib.reviews/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 | $0.00365 | $0.00365 |
| Opus 5 | $0.00182 | $0.00182 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
lib.reviews 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.
What it actually says
lib.reviews Agent Notes
This repository powers the lib.reviews platform. It includes legacy patterns and is being modernized.
Tech Stack
- Runtime/language: Node.js (>=22), TypeScript (ESM)
- Backend: Express, Handlebars (
hbs),config - Data/search: PostgreSQL (
pg), sessions (connect-pg-simple), Elasticsearch client - Frontend: Vite (MPA) + TS modules, PicoCSS, jQuery, ProseMirror, PostCSS
- Tooling: Biome (lint/format), AVA (+ Supertest/Nock/JSdom), TypeDoc
Guidance for Agents
- Preserve behavior unless explicitly told otherwise; many routes have implicit dependencies.
- Code comments should describe the code that is there, not legacy behavior or intermediate steps.
- Code comments are NOT a tool to support user-agent communication; they must only be added if they have long-term value.
- If asked for a commit message, use Conventional Commits: subject ≤50 chars, body lines ≤72 chars, ≤4 bullets, describe only the current diff.
- In TypeScript doc comments, omit types in
@paramtags. - If you touch TS/JS/backend, ensure
npm run lint,npm run typecheck, andnpm run testpass.npm run testmay be blocked in restricted sandboxes; ask before running or tell the user to run it locally / with elevation. - During CSS-only iteration, you can usually rely on Vite HMR/dev server for feedback; run
npm run build:frontendwhen changing PostCSS features (nesting/mixins), when the user reports Vite errors, or when anything about the CSS pipeline/bundling changes.
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 First seen · 20 lines · 365 tokens per session scan A 854a25515b74
lib.reviews AGENTS.md is an instructions file published in the GitHub repository permacommons/lib.reviews (201 stars, last pushed 10d ago), licensed CC0-1.0. It adds 365 tokens to every session, about $0.0018 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 2026-08-30.
Other instructions, from other repositories
leoric AGENTS.md
Instructions for cyjake/leoric, covering agent guidelines, project overview, commands, architecture and conventions.
supabase studio-composition-patterns.instructions.md
Instructions for supabase/supabase, covering react composition patterns review rules, core principle, when to flag, 1. boolean prop proliferation (high) and 2. render props instead of children (medium).
supabase studio-shortcuts.instructions.md
Instructions for supabase/supabase, covering studio shortcut review rules, core principle, when to flag, preferred pattern and search inputs.
supabase studio-e2e-tests.instructions.md
Instructions for supabase/supabase, covering studio e2e test review rules, selector priority (best to worst), patterns to flag and good practices to encourage.
supabase studio-testing.instructions.md
Instructions for supabase/supabase, covering studio testing review rules, core principle, when to comment, which test type to suggest and reference.
supabase studio-copy.instructions.md
Instructions for supabase/supabase, covering studio ui copy and agent checklist (not in the design doc).