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/julien777z/code-review-action/agents-mdgit clone --depth 1 https://github.com/julien777z/code-review-actionWrote 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/julien777z/code-review-action/agents-md)<a href="https://agentmods.dev/instructions/julien777z/code-review-action/agents-md"><img src="https://agentmods.dev/badge/instructions/julien777z/code-review-action/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 | $0.17780 | $0.17780 |
| Opus 5 | $0.08890 | $0.08890 |
| Sonnet 5 | $0.03556 | $0.03556 |
| Haiku 4.5 | $0.01778 | $0.01778 |
Grade B, and why
code-review-action AGENTS.md scanned grade B with 1 finding 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo systemctl start docker 2>/dev/null \ This is a copy
94% identical to agent-sync-action AGENTS.md — 59 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Generated by Agent Sync Action. Do not edit this file directly.
The canonical project rules live in .agents/rules/.
GitHub Rules
Workflows
- Keep
runsteps declarative. Invoke checked-in scripts for control flow, validation, filesystem changes, or other implementation logic instead of embedding arbitrary shell or program code in workflow YAML; place those scripts under.github/scripts/and prefer Python. - Do not hard-code runtime versions when a shared action, reusable workflow, or repository version file supplies them; omit
python-versionwhen shared Python automation provides it, and usenode-version-file: ".nvmrc"for Node.js workflows. - Do not add glue steps that only read versions or forward setup data. Pass repository-owned version files and inputs directly to the action that uses them whenever supported.
- Keep workflow files concise: merge related setup and dependency commands into one clearly named generic step when their execution order and conditions allow it. Do not split tool or package installation into separate steps merely by dependency.
- Environment configuration that tunes a tool — retry counts, timeouts, cache locations, path entries — belongs in the step that installs or runs that tool, not in a step of its own. A step whose whole body writes to
$GITHUB_ENVis named for a concern rather than an action, and the reader has to look elsewhere to find out which later step it affects. Write those exports at the end of the owning step so the setting and its consumer stay together. - Add an explanatory comment when an edge case requires an explicit version override.
- Use version-tagged GitHub Actions such as
actions/checkout@v4andactions/setup-python@v5, not full commit SHAs.
Branches and Pull Requests
- Keep pull requests focused and give them descriptive titles and descriptions; request appropriate reviewers when the repository workflow requires them.
- A pull request description covers the changes in that pull request and nothing else. Leave out alternatives considered and rejected, work deferred to a later change, and the reasoning behind not doing something.
- Repositories are independent. A pull request in one repository does not describe, reference, or explain changes made in another.
- When additional work arrives on a non-default branch, retain that branch and add the work to its pull request even when the task could be reviewed independently.
- Query the current branch's pull request before creating one. Reuse it while it is open, or create one from the current branch when none exists.
- Create a separate branch only when the user asks or the current branch's pull request is already merged; start post-merge work from the default branch.
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.
- 4d ago First seen · 1,213 lines · 17,780 tokens per session scan B 5b09c7864bc2
code-review-action AGENTS.md is an instructions file published in the GitHub repository julien777z/code-review-action (2 stars, last pushed 7d ago), licensed MIT. It adds 17,780 tokens to every session, about $0.0889 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). It is 94% identical to agent-sync-action AGENTS.md, differing in 59 lines, and is treated as a copy.
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.