Agent skill

Agy Reviewer

by keli-wen in keli-wen/agy-staff

Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design.

MITAuto-check passed

Install Agy Reviewer

skills CLI
$ npx skills add keli-wen/agy-staff --skill agy-reviewer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install keli-wen/agy-staff agy-reviewer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/keli-wen/agy-staff.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pi-skills/agy-reviewer .claude/skills/agy-reviewer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agy-reviewer
GitHub stars
733
Token cost
~1.5k tokens
SKILL.md length
747 words
Files
3 (incl. references)
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design.

  • The user says /skill:agy-reviewer
  • SKILL.md covers Locating the companion, The review subject is the prompt, Collecting the result and Flags (all optional), plus 3 more sections
  • Calls node
  • Have agy review this

What it does

Agy Reviewer is an agent skill from keli-wen/agy-staff. Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Use when the user says /skill:agy-reviewer, "have agy review this", "second opinion on my diff/PR/plan", or after finishing work and wanting an independent verifier that does not share the host model's blind spots.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/code-review.md` and `references/general-review.md`).

The repository describes itself as: Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code and OpenAI Codex. The licence is MIT.

When your agent uses it

  • The user says /skill:agy-reviewer
  • Have agy review this
  • Second opinion on my diff/PR/plan
  • After finishing work and wanting an independent verifier that does not share the host models blind spots

Example prompts

  • “have agy review this”
  • “second opinion on my diff/PR/plan”
  • “/agy-reviewer”

What it can do on your machine

Read from SKILL.md and the folder at commit 65a1ab4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agy Reviewer loads about 1.5k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 96 tokens; SKILL.md has 747 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from keli-wen/agy-staff at commit 65a1ab4, republished under its MIT licence (© keli-wen). 747 words, ~1,477 tokens.

Download SKILL.mdSave it as .claude/skills/agy-reviewer/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
agy-reviewer
description
Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Use when the user says /skill:agy-reviewer, "have agy review this", "second opinion on my diff/PR/plan", or after finishing work and wanting an independent verifier that does not share the host model's blind spots.
<!-- Generated from skills/reviewer/SKILL.md; run npm run generate:pi. Do not edit here. -->

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.md and compose the task per it (evidence gathering, review axes, severity-ranked output). --json belongs to this flavor only.
  • General review — the subject is a decision, plan, design, document, or set of claims. Read references/general-review.md and 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:

bash
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.

Collecting the result

The command returns a job id. Read ../agy-jobs/SKILL.md for result collection and recovery: dispatch, wait for the final result, then validate as needed. Do not proactively observe progress, read logs or inspect intermediate artifacts while running. Observe only when the user explicitly asks for progress; diagnose a failure or a result requiring intervention under the jobs protocol.

Flags (all optional)

  • --json — schema-enforced JSON findings (verdict/summary/findings/could_not_verify) instead of markdown. Code-review flavor only, and only when the user asks for machine-readable output.
  • --restricted / --unrestricted — permission profile. review defaults to unrestricted, so it works out of the box and can run tests or reproduce a bug when the request asks for it. --restricted is the opt-in hardening path: agy may then only use allowlisted tools, so it needs the setup flow's evidence-gathering allowlist to be useful — and some native agy tools ignore allow-rules headless, so restricted runs can still come back empty.
  • --model <id> / --effort low|medium|high (default gemini-3.8-flash-medium), --continue (or --conversation <id>), --timeout <dur> (default 60m, maximum 120m hard execution limit).
  • --prompt <text> / --prompt-file <path> / --stdin — the task, from exactly one of these three sources. Use file/stdin for long prompts (a composed task with the flavor framing usually is one).
Show full SKILL.md (270 more words)Show less

Reviewing untrusted content

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 --restricted (it may fail closed, and some native tools ignore allow-rules) or run the review in an isolated checkout.

Rules

  • Return the companion stdout verbatim — no commentary, no fixes, no softening of findings.
  • Pass the user's explicit authorizations through to the task string verbatim. The prompt template default-denies costly or irreversible side effects (commits/pushes, deleting files outside the workspace, side-effectful network calls, commands that burn paid API quota); that default opens only when the request itself asks for the operation — so keep "run the e2e tests" or "call the staging API" in the prompt instead of trimming it.
  • Empty responses from a --restricted run: relay the companion's guidance (run the setup flow once, or drop --restricted).
  • For errors and recovery, follow ../agy-jobs/SKILL.md.

For an existing conversation, --continue / --conversation <id> inherit its recorded model and permission profile unless explicitly overridden. The unrestricted defaults above apply to new tasks.

Host compatibility

When this skill or its referenced instructions require a tool that the current environment does not provide, use available capabilities to achieve an equivalent result. Adapt only the tool-specific execution method; preserve the task goal, authorization requirements, explicit confirmation steps, result delivery, and stopping conditions.

If an equivalent result cannot be achieved, or you cannot establish that an alternative is equivalent, explain the missing capability and its impact, and ask the user for help. Do not silently skip requirements or bypass the environment's restrictions.

© keli-wen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in pi-skills/agy-reviewer of keli-wen/agy-staff.

  • SKILL.md
  • references/code-review.md
  • references/general-review.md

Open the folder on GitHubat commit 65a1ab4

Compare with similar skills

Agy Reviewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agy Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agy Reviewer this skillkeli-wen/agy-staff733—~1.5kAutomated safety check: PassMIT
Second Opinion Code Reviewtrailofbits/skills7.5k—~1.3kAutomated safety check: NotesCC-BY-SA-4.0
Review Pending PR Reviewsnrwl/nx29k—~3.9kAutomated safety check: PassMIT
Reviewthedaviddias/Front-End-Checklist74k—~556Automated safety check: PassMIT
ReviewClickHouse/ClickHouse50k—~8kAutomated safety check: NotesApache-2.0
Docling Pull Request Reviewdocling-project/docling69k—~1kAutomated safety check: PassMIT

Similar skills

  • Second Opinion Code Review

    trailofbits/skills

    Official

    Runs an independent review of uncommitted changes, a branch diff or one commit through the Codex or Antigravity CLI, or both, and reports their findings.

    7.5k GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Review, grill, edit, and post pending PR review drafts saved by /review-pr (or its batch/cron runners).

    29k GitHub stars~3.9k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Review

    thedaviddias/Front-End-Checklist

    A skill your agent uses when applies to product pages, local business pages, recipes, apps, books, and any page that aggregates user reviews.

    74k GitHub stars~556 tokensUpdated 4 days ago
    Marketing & SEOAuto-check passed
  • Review

    ClickHouse/ClickHouse

    Review a ClickHouse Pull Request for correctness, safety, performance, and compliance.

    50k GitHub stars~8k tokensUpdated today
    DatabasesAuto-check: notes
  • Docling Pull Request Review

    docling-project/docling

    Reviews or re-reviews a Docling pull request in fixed stages, with findings that can be reproduced and an explicit record of every check that was run.

    69k GitHub stars~1k tokensUpdated today
    DevelopmentAuto-check passed
  • Pre-Landing PR Review

    garrytan/gstack

    Reviews your diff against the base branch before merge, looking for SQL safety problems, LLM trust boundary violations, conditional side effects and other structural issues.

    136k GitHub stars~20k tokensUpdated today
    DevelopmentAuto-check: notes

More from keli-wen/agy-staff

All 13 skills in this repo
  • Jobs

    keli-wen/agy-staff

    Manage agy staffer background jobs - collect results, check status, cancel, follow-up conversation, and setup.

    733 GitHub stars~2.7k tokensUpdated 4 days ago
    Auto-check passed
  • Reviewer

    keli-wen/agy-staff

    Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design.

    733 GitHub stars~1.3k tokensUpdated 4 days ago
    Auto-check passed
  • Agy Ask

    keli-wen/agy-staff

    Ask Google's Antigravity CLI (agy staffer, fast Gemini) a cheap one-shot question - the fast zero-tool mode and the post-install smoke test.

    733 GitHub stars~915 tokensUpdated 4 days ago
    Auto-check passed
  • Agy Lead

    keli-wen/agy-staff

    Orchestrate an ongoing task with AGY while the current agent owns key decisions, review, and delivery.

    733 GitHub stars~1.6k tokensUpdated 4 days ago
    Auto-check passed
  • Agy Researcher

    keli-wen/agy-staff

    Delegate a deep research or survey task to Google's Antigravity CLI (agy staffer, fast Gemini).

    733 GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed
  • Agy Researcher

    keli-wen/agy-staff

    Delegate a deep research or survey task to Google's Antigravity CLI (agy staffer, fast Gemini).

    733 GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed

Questions about Agy Reviewer

What does Agy Reviewer do?

Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Agy Reviewer is an agent skill from keli-wen/agy-staff. Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design.

When should I use Agy Reviewer?

Agy Reviewer fits situations like: the user says /skill:agy-reviewer; have agy review this; second opinion on my diff/PR/plan; after finishing work and wanting an independent verifier that does not share the host models blind spots.

How do I install Agy Reviewer in Claude Code?

Run `npx skills add keli-wen/agy-staff --skill agy-reviewer -a claude-code`. Or copy the skill folder (pi-skills/agy-reviewer in keli-wen/agy-staff) into .claude/skills/agy-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Agy Reviewer in Codex?

Run `npx skills add keli-wen/agy-staff --skill agy-reviewer -a codex`. Or copy the skill folder (pi-skills/agy-reviewer in keli-wen/agy-staff) into .agents/skills/agy-reviewer in your project. Codex loads it when a task matches its description.

Can I use Agy Reviewer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add keli-wen/agy-staff --skill agy-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agy-reviewer, .gemini/skills/agy-reviewer, .github/skills/agy-reviewer and .opencode/skills/agy-reviewer in your project.

What does Agy Reviewer need to run?

Going by SKILL.md and its folder, Agy Reviewer needs the command-line tools its instructions call (node).

Does Agy Reviewer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agy Reviewer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agy Reviewer use?

Agy Reviewer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agy Reviewer use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Agy Reviewer?

Skills that share tags, products or a category with Agy Reviewer: Second Opinion Code Review (trailofbits/skills, 7.5k stars), Review Pending PR Reviews (nrwl/nx, 29k stars), Review (thedaviddias/Front-End-Checklist, 74k stars) and Review (ClickHouse/ClickHouse, 50k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agy Reviewer?

keli-wen (a GitHub user) maintains it in keli-wen/agy-staff, which has 733 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 7, 2026.

Source: keli-wen/agy-staff on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.