Borrowing it
Nothing to install: this file belongs to figitaki/reviews. 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/figitaki/reviews/main/AGENTS.mdgit clone --depth 1 https://github.com/figitaki/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/figitaki/reviews/agents-md)<a href="https://agentmods.dev/instructions/figitaki/reviews/agents-md"><img src="https://agentmods.dev/badge/instructions/figitaki/reviews/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/figitaki/reviews/agents-md"><img src="https://agentmods.dev/badge/instructions/figitaki/reviews/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 | $0.01637 | $0.01637 |
| Opus 5.5 | $0.00655 | $0.00655 |
| Sonnet 5.5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
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 20d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviews
Reviews is a code-review tool for arbitrary diffs, not only GitHub PRs. An author pushes a diff plus a review packet (markdown that orders and annotates hunks into sections); reviewers read the packet, comment, and decide per section; --update adds patchsets.
Stack: Elixir 1.20 / Phoenix 1.8 / LiveView 1.2 (web), Rust CLI in cli/, Postgres, vanilla @pierre/diffs for diff rendering (no React). Bun manages assets/.
This file is for every coding agent (Claude Code, Codex, Cursor, …). CLAUDE.md is a symlink to it. Framework-level Phoenix/Elixir rules live in .claude/rules/phoenix-usage-rules.md; read that file before editing Elixir, HEEx or asset files.
Commands
| Task | Command |
|---|---|
| First setup | mix setup (deps, DB, assets) and cd assets && bun install |
| Dev server | ./bin/server (sources .env.local for GitHub OAuth, then mix phx.server on :4000). Check lsof -iTCP:4000 -sTCP:LISTEN first; a second server fails on bind. |
| Before committing | mix precommit (compile with warnings as errors, unused deps, format, test) |
| Elixir tests | mix test. Parallel runs or worktrees: MIX_TEST_PARTITION=<name> mix test gives each its own DB. |
| JS unit tests | cd assets && bun run test |
| Assets | mix assets.build (CI runs it; tailwind needs NODE_PATH, already wired) |
| CLI | cd cli && cargo build --release, cargo test, cargo clippy --all-targets -- -D warnings, cargo fmt --check |
| Preview a change as a review | reviews push from any checkout, then open the printed /r/<slug> URL; reviews push --update <slug> adds a patchset; reviews push --dry-run validates without sending |
CI (.github/workflows/ci.yml) runs format check, compile with warnings as errors, bun install --frozen-lockfile, mix assets.build, and mix test. Match it locally before pushing.
Where things are
lib/reviews/contexts:reviews.ex(reviews, patchsets),threads.ex,packet_section_decisions.ex,anchoring.ex,accounts.ex(users, agent identities, API tokens),code_snapshots.ex+code_storage/(optional code.storage backend).lib/reviews_web/live/review_live.exis the review screen; its packet UI is inreview_live/packet_components.ex, diff components inreview_live/diff_components.ex.settings_live.exholds identities and tokens.lib/reviews_web/controllers/api/is the JSON API the CLI uses.docs/CONTRACTS.mddocuments it and the LiveView hook events; update it with any API change.assets/js/hooks/diff_renderer.jsmounts Pierre; rendering code is inassets/js/diff_renderer/; dataset parsing goes through Zod schemas inassets/js/schemas.js.assets/css/app.cssimportstokens.css,components.css,packet.css(review UI,.review-*/.rev-*),landing.css,product-shell.css. Use the--ds-*tokens; do not add hex colours in components..plans/holds design plans and is tracked. Read the plan for the area you touch before changing it..plans/market-scan-2026-10.mdlists product ideas with prior art.skills/are the agent skills shipped with the CLI installer (overview, writing packets, using Reviews locally). Keep them in sync with CLI flags.docs/RELEASE.mdis the release process;CHANGELOG.mdhas an Unreleased section to add to.
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.
- 20d ago Changed · -432 lines · -5,409 tokens per session scan C → A 2f2404782887
- 2mo ago First seen · 504 lines · 7,046 tokens per session scan C 695187726332
reviews AGENTS.md is an instructions file published in the GitHub repository figitaki/reviews (6 stars, last pushed 20d ago), licensed MIT. It adds 1,637 tokens to every session, about $0.0065 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.
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.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.