Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/keli-wen/agy-staffnpx agentmods add skills/keli-wen/agy-staff/agy-reviewerWrote 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/skills/keli-wen/agy-staff/agy-reviewer)<a href="https://agentmods.dev/skills/keli-wen/agy-staff/agy-reviewer"><img src="https://agentmods.dev/badge/skills/keli-wen/agy-staff/agy-reviewer/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/skills/keli-wen/agy-staff/agy-reviewer"><img src="https://agentmods.dev/badge/skills/keli-wen/agy-staff/agy-reviewer.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 | $0.00096 | $0.01308 |
| Opus 5 | $0.00048 | $0.00654 |
| Sonnet 5 | $0.00019 | $0.00262 |
| Haiku 4.5 | $0.00010 | $0.00131 |
Grade B, and why
agy-reviewer 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 2d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
An unrestricted review of code from an untrusted author (a PR from a stranger, a patch from an unknown source) means prompt injection in that content could run arbitrary commands. For those reviews, consider `--restricte This is a copy
86% identical to reviewer — 22 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agy reviewer
Run a second-opinion review through the agy staffer. You are a thin shell: compose the task, run the companion, return agy's review verbatim. Never fix the issues it finds.
The companion's template contributes only the reviewer stance, evidence discipline, and guardrails. Everything flavor-specific travels in the task string you compose — so pick the flavor first:
- Code review — the subject is code: a PR, a branch/ref, the working tree, a patch file, specific files. Read
references/code-review.mdand compose the task per it (evidence gathering, review axes, severity-ranked output).--jsonbelongs to this flavor only. - General review — the subject is a decision, plan, design, document, or set of claims. Read
references/general-review.mdand compose the task per it (multi-angle challenge). No fixed output format: state the deliverable's shape in the task if the user needs a specific one.
Locating the companion
This skill file lives at <plugin-root>/pi-skills/agy-reviewer/SKILL.md; resolve the companion path relative to this skill directory:
node "<skill-dir>/../../companion/agy-companion.mjs" review [flags] --prompt "what to review"
Pass the review subject verbatim via --prompt; use --prompt-file <path> or --stdin for long text, which a composed task usually needs.
[!IMPORTANT] Run this command unsandboxed — agy needs a localhost port and its OAuth token file, which harness sandboxes hide. In Codex, request escalated permissions for the command. Details:
../agy-jobs/references/troubleshooting.md.
The review subject is the prompt
review is prompt-based: the user's request plus the flavor's framing is the task string. Do not gather diffs, write patch files, or translate the request into flags — agy collects the evidence itself. If the subject is ambiguous, agy reports the ambiguity instead of guessing; relay that and let the user sharpen the request. A task string is required; review with no subject exits with an error.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed 92ae888b66af
- 3d ago Changed · -2 lines d9e89f5657fe
- 7d ago First seen · 65 lines · 96 tokens per session scan B f2b0e10ad300
agy-reviewer is a skill published in the GitHub repository keli-wen/agy-staff (131 stars, last pushed yesterday), licensed MIT. It adds 96 tokens to every session and 1,308 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). It is 86% identical to reviewer, differing in 22 lines, and is treated as a copy.
Other skills, from other repositories
mantis-plan
Formulates a targeted defensive security reviewing plan based on the active threat model and historical learnings. Use when starting a security review campaign to map the codebase boundaries and generate a roadmap (workspace/plan.json). Don't use for executing code reviews, writing test scripts, or patching code.
mantis-researcher
Audits production source code files based on the strategy in workspace/plan.json. Use when a review plan exists and you need to perform static analysis and deep-dive reviews of targeted files. Don't use for planning, deduplicating, or writing patches.
mantis-review
Independently reviews findings and filters out false positives. Use when consolidated findings need validation against the actual source code. Don't use for reproducing crashes or patching code.
mantis-summarize
Pre-processes the repository by generating security-focused summaries (mantis-summary.md) for each directory to make planning and research more efficient. Use when starting a review campaign to map the codebase before threat modeling and planning. Don't use for executing code reviews, writing test scripts, or patching…
mantis-launch
Launches automated vulnerability review campaigns on target files or repositories. Use to initiate Mantis vulnerability review pipelines with automated preflight checks, environment auto-configuration, and runtime overrides (sandboxes, models, endpoints). Don't use for configuring settings without scanning or for…
ocr
AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives. Use when asked to review code, check a PR, analyze changes, or perform code review.