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 Jewgah/claude-code-skills --skill review-deepgit clone --depth 1 https://github.com/Jewgah/claude-code-skillsWrote 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/jewgah/claude-code-skills/review-deep)<a href="https://agentmods.dev/skills/jewgah/claude-code-skills/review-deep"><img src="https://agentmods.dev/badge/skills/jewgah/claude-code-skills/review-deep/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/jewgah/claude-code-skills/review-deep"><img src="https://agentmods.dev/badge/skills/jewgah/claude-code-skills/review-deep.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 | $0.00020 | $0.02308 |
| Opus 5 | $0.00010 | $0.01154 |
| Sonnet 5 | $0.00004 | $0.00462 |
| Haiku 4.5 | $0.00002 | $0.00231 |
Grade A, and why
review-deep 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 12d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Multi-Agent Code Review
Perform an exhaustive, multi-perspective code review using parallel agents that cross-check each other. This catches bugs that a single-pass review misses — especially race conditions, state inconsistencies, and cross-file dependency breaks.
When to use this vs. the others — reach for
/reviewfor a fast single-pass pre-commit check (no subagents); use this for a risky local change you want stress-tested before it ships; use/code-reviewonce it's a GitHub PR (it posts inline comments and scores confidence). This skill reviews the local working tree and prints to the terminal — it does NOT post to GitHub. If the change is already a PR, prefer/code-review.
Step 1: Gather Changes
- Determine scope from
$ARGUMENTS:- "staged":
git diff --cached - "unstaged":
git diff - "last-commit":
git rev-parse HEAD~1 >/dev/null 2>&1 && git diff HEAD~1 || git diff $(git hash-object -t tree /dev/null)(falls back to the empty tree on a repo's first commit) - "branch" / "pr": review the whole branch against its base. Detect the default branch robustly:
BASE=$(git merge-base HEAD "$(git symbolic-ref --quiet --short refs/remotes/origin/HEAD 2>/dev/null | sed 's@^origin/@@' || echo main)" 2>/dev/null || git merge-base HEAD main 2>/dev/null || git merge-base HEAD master). IfBASEis still empty (non-standard default branch), fall back togit diffand state which base you used. Thengit diff $BASE...HEAD. - Otherwise: both
git diffandgit diff --cached
- "staged":
- Run
git statusfor context. - Empty-diff guard: if the chosen diff is empty, stop and report "No changes in scope to review" — do not launch agents.
- Read the COMPLETE content of every changed file (not just the diff).
- Load conventions: read the nearest
CLAUDE.md(and any project review notes) so agents can flag convention violations — project-specific patterns, naming conventions, tenant-scoping rules — not just generic bugs. Pass the relevant conventions into each agent prompt.
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.
- 12d ago First seen · 101 lines · 20 tokens per session scan A fde4c24231a5
review-deep is a skill published in the GitHub repository Jewgah/claude-code-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 2,308 once invoked, about $0.0001 per session on Opus 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
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
agent-design-best-practices
Best practices for designing Claude Code agent files (.claude/agents/.md). This skill should be used when writing or reviewing agent markdown files to ensure proper design with focused domains, correct tool access, reusable definitions, and separation of capabilities from lifecycle. Combines Anthropic's official…
graphify-dotnet
Use graphify-dotnet to generate codebase knowledge graphs, architecture snapshots, and exportable repository maps from .NET or polyglot source trees, with optional AI-enriched semantic relationships. USE FOR: graphify commands; graph JSON, HTML, SVG, Cypher, Markdown, and Obsidian exports; repository map and…
map-codebase
Deep architecture report that fans out parallel inspections across different aspects of the codebase (structure, tech stack, APIs, patterns, data flow, dependencies, testing) and synthesizes findings into a comprehensive document at .turbo/codebase-map.md and .turbo/codebase-map.html. Use when the user asks to "map…
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…