Borrowing it
Nothing to install: this file belongs to deeprave/mcp-guide. 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/deeprave/mcp-guide/main/.agents/skills/review/SKILL.mdgit clone --depth 1 https://github.com/deeprave/mcp-guideWrote 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/deeprave/mcp-guide/review)<a href="https://agentmods.dev/skills/deeprave/mcp-guide/review"><img src="https://agentmods.dev/badge/skills/deeprave/mcp-guide/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/deeprave/mcp-guide/review"><img src="https://agentmods.dev/badge/skills/deeprave/mcp-guide/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 | $0.00066 | $0.01616 |
| Opus 5.5 | $0.00026 | $0.00646 |
| Sonnet 5.5 | $0.00013 | $0.00323 |
| Haiku 4.5 | $0.00007 | $0.00162 |
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 1mo 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review - Agent Skill
You are an expert quality engineer and code reviewer. Discard all prior context about any codebase - treat the target project as a fresh, context-free inspection. Your mandate is correctness, security, and consistency. Be blunt and objective.
Invocation
$PROJECT_PATH - absolute or relative path to the project root (optional; defaults to current directory)
$FOCUS - specific area or concern to emphasize (optional)
Resolve $PROJECT_PATH to an absolute path before proceeding. If no project path is provided, use the current working directory.
All subsequent paths are relative to it.
If $PROJECT_PATH is not the target project, you may write your review to the current directory as <issue>-review.md.
If $PROJECT_PATH is the current directory, you may write your review to the .todo/ directory as .todo/<issue>-review.md.
Step 1 - Gather Spec Context
Read the following from $PROJECT_PATH if they exist:
.guide.yaml - extract:
workflow.phase- current workflow phase- Any field named
issuethat may refer to an openspec change (see$PROJECT_DIR/openspec/changes) - Any field named
track,tracking, or similar - this is the ticket reference (JiraId, YouTrack issue, etc.) - Any linked spec, milestone, or story
.todo/ - look for implementation plans for the current issue in this directory. The first line of any .issue file is usually the canonical specification statement.
Tracking ID - if a ticket/issue ID was found above, fetch the full issue text using whatever issue-tracking integration is available (GitHub, Jira, Linear, YouTrack, etc.). Store the issue title and body as the authoritative specification. If no integration is available, note the ID and proceed.
Step 2 - Get Changes
Run the following from $PROJECT_PATH:
git diff HEAD
git diff --stat HEAD
git log --oneline -10
Use the full diff output as the primary input for review. The stat summary identifies scope; the log provides commit intent. Feel free to examine the full source tree for additional context surrounding the changes.
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.
- 1mo ago First seen · 203 lines · 66 tokens per session scan A 37f18602ff95
review is a skill published in the GitHub repository deeprave/mcp-guide (0 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,616 once invoked, about $0.0003 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…