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 skills add michaelcjoseph/agent-coding-setup --skill reviewgit clone --depth 1 https://github.com/michaelcjoseph/agent-coding-setupWrote 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/michaelcjoseph/agent-coding-setup/review)<a href="https://agentmods.dev/skills/michaelcjoseph/agent-coding-setup/review"><img src="https://agentmods.dev/badge/skills/michaelcjoseph/agent-coding-setup/review/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/michaelcjoseph/agent-coding-setup/review"><img src="https://agentmods.dev/badge/skills/michaelcjoseph/agent-coding-setup/review.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 | $0.00000 | $0.03589 |
| Opus 5.5 | $0.00000 | $0.01436 |
| Sonnet 5.5 | $0.00000 | $0.00718 |
| Haiku 4.5 | $0.00000 | $0.00359 |
Grade A, and why
review 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 2mo 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review
Run the full review panel — test-specialist, security-auditor, code-reviewer, code-simplifier, and architecture-reviewer — in parallel against the current uncommitted working tree, then return one consolidated verdict.
Use this as a pre-commit gate, after exploratory work outside /work, or any time you want a comprehensive review of "what's on disk right now."
Usage
/review
No arguments. The skill always operates on the current working tree (staged + unstaged + untracked).
Scope
"Uncommitted changes" means everything that differs from HEAD:
- Tracked changes —
git diff HEAD --name-only(covers both staged and unstaged) - Untracked files — entries from
git status --porcelainwhose status code is??
If both lists are empty, exit immediately with "Nothing to review — working tree matches HEAD." Do not launch any agents.
Constraints
/reviewdoes not modify production code. The four reviewers (security-auditor,code-reviewer,code-simplifier,architecture-reviewer) are read-only.test-specialistis the one carve-out: it may add new test files and fix failures introduced by its own new tests — but never bootstrap test infra, modify unrelated tests, or touch non-test source. The user decides what to do with the verdict.- If an agent errors out (timeout, missing definition, runtime failure, or returns an unparseable response the synthesizer can't extract a verdict and findings from), mark it
UNAVAILABLEwith a one-line reason in the per-agent results, do not retry, and compute the overall verdict from the remaining agents.
Why test-specialist is allowed to write (but not bootstrap): the goal of
/reviewis comprehensive pre-commit confidence, and "no test exists for the new code" is a gap the panel should close, not just report. Bootstrapping a test framework, in contrast, is a structural project decision (framework choice, layout, scripts) that belongs in/work, not as a side effect of a review pass. New test files are flagged under "Per-agent results" so the user knows they weren't themselves reviewed in this pass — they'll be on the next/reviewrun.
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.
- 2mo ago First seen · 307 lines · 0 tokens per session scan A 0b58ce33a99d
review is a skill published in the GitHub repository michaelcjoseph/agent-coding-setup (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,589 tokens. 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 skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…