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 Jamie-BitFlight/claude_skills --skill code-review-claude-skillsgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_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/jamie-bitflight/claude_skills/code-review-claude-skills)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/code-review-claude-skills"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/code-review-claude-skills/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/jamie-bitflight/claude_skills/code-review-claude-skills"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/code-review-claude-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 18 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 83 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium Agent Snooping · line 89 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00039 | $0.01126 |
| Opus 5 | $0.00019 | $0.00563 |
| Sonnet 5 | $0.00008 | $0.00225 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
code-review-claude-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Skills and Agent Code Review Patterns
Stack-specific rules loaded by dh:code-reviewer when SKILL.md, agent frontmatter files, or plugin.json files are detected.
Frontmatter Validity
namemust match the containing directory name exactly — mismatch causes lookup failuresnamemust satisfy^[a-z][a-z0-9-]*$— lowercase letters, digits, hyphens onlydescriptionmust be a single-line string — no YAML multiline indicators (>-,|-,>,|)toolsfield (in agents) must be a comma-separated string, not a YAML array —Read, Grep, Globnot[Read, Grep, Glob]modelmust be one ofsonnet,opus,haiku, orinherit— no version strings, no full model IDs- Run
uvx skilllint@latest check --fix <path>after every frontmatter edit — auto-fixes YAML formatting issues including quoting
Description Quality
- The description must contain specific trigger keywords
- First 1024 characters are most important — front-load trigger conditions and activation signals
- Preferred trigger openers: "Use when", "Activates on", "Triggers on", "Loaded automatically when"
- Descriptions must be third-person ("Generates commit messages" not "I can help you generate")
- Vague descriptions produce missed triggers — "Helps with Python stuff" is a blocking finding
Token Budget
- Skills must not include information Claude already has from training (general language patterns, well-known APIs, common idioms)
- Include only project-specific context, conventions, and domain knowledge that Claude cannot infer
- Skills over 4000 tokens should be flagged as oversized (warn); over 6400 tokens are blocking
- Inline examples are valuable — prefer 2-3 focused examples over exhaustive lists
Scope of Tools
allowed-toolsin agent frontmatter must be scoped to the minimum required for the agent's task- Agents that only review code must not have
WriteorEditin their tools list - Verification-only agents must not have destructive tools
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.
- 7d ago First seen · 94 lines · 39 tokens per session scan A a4f84bd5b123
code-review-claude-skills is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,126 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
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…