Borrowing it
Nothing to install: this file belongs to atra-consulting/coding-with-ai-lab. 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/atra-consulting/coding-with-ai-lab/main/.claude/skills/review/SKILL.mdgit clone --depth 1 https://github.com/atra-consulting/coding-with-ai-labWrote 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/atra-consulting/coding-with-ai-lab/review)<a href="https://agentmods.dev/skills/atra-consulting/coding-with-ai-lab/review"><img src="https://agentmods.dev/badge/skills/atra-consulting/coding-with-ai-lab/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/atra-consulting/coding-with-ai-lab/review"><img src="https://agentmods.dev/badge/skills/atra-consulting/coding-with-ai-lab/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 | $0.00033 | $0.07825 |
| Opus 5.5 | $0.00013 | $0.03130 |
| Sonnet 5.5 | $0.00007 | $0.01565 |
| Haiku 4.5 | $0.00003 | $0.00783 |
Grade A, and why
review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 830 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Skill
Claude Code + Copilot CLI: this skill runs in both. "Ask the user" =
AskUserQuestion(Claude Code) /ask_user(Copilot CLI). "Start a subagent" =Agent/Tasktool (Claude Code) /tasktool (Copilot CLI), with the agent's name as the type.$ARGUMENTS= the text typed after the skill name.
You are executing the review skill, which provides local code review with a multi-round review & fix cycle on a feature branch vs main.
RESULTS DISPLAY GUARANTEE
The skill MUST ALWAYS surface its review results. It never finishes silently. This holds in every mode — embedded (called from an agent prompt or another skill) or stand-alone, dry-run or normal.
Every run MUST produce the full review content. One of these two carries it:
- Markdown file — normal mode. The review is written to
[docs_folder]/reviews/REVIEW-<branch>.md(PHASE 6). - On screen — dry-run mode. The full review content is displayed in the conversation instead of writing a file (PHASE 6).
On top of that, the PHASE 7 summary is always printed to screen. In every mode. Including embedded. So the caller and the user both see the outcome.
Embedded mode skips only PHASE 0 (plan-mode check and header) and PHASE 1.3 (task-understanding confirmation). It still runs PHASE 6 and PHASE 7. So it still writes the review file and prints the summary.
If a run reaches the end without producing either the Markdown file or the on-screen content, that is a bug. Produce the on-screen content before stopping.
Writing Style
Short and brief. Short sentences. Simple words non-native speakers understand. No passive voice. Use sentence fragments.
FILE PATH DISPLAY RULE
When displaying any file path to the user, ALWAYS use the full absolute path. Get the project root with pwd and prepend it to relative paths. Example: /Users/dev/project/docs/reviews/REVIEW-add-feature.md instead of docs/reviews/REVIEW-add-feature.md. This lets users Command-click paths in the terminal to open them.
What ships with it
1 file 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.
- 9d ago Changed · +5 lines · -2 tokens per session 9ad17b3d6f19
- 20d ago Changed 2e9091ee3b9f
- 2mo ago First seen · 825 lines · 35 tokens per session scan A b6346a5b22cf
review is a skill published in the GitHub repository atra-consulting/coding-with-ai-lab (5 stars, last pushed 8d ago), licensed MIT. It adds 33 tokens to every session and 7,825 once invoked, about $0.0001 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 skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
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…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…