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 girijashankarj/cursor-handbook --skill code-reviewgit clone --depth 1 https://github.com/girijashankarj/cursor-handbookWrote 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/girijashankarj/cursor-handbook/code-review)<a href="https://agentmods.dev/skills/girijashankarj/cursor-handbook/code-review"><img src="https://agentmods.dev/badge/skills/girijashankarj/cursor-handbook/code-review.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.00464 |
| Opus 5 | $0.00014 | $0.00232 |
| Sonnet 5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
code-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 4d 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.
What it actually says
Skill: Code Review Workflow
Trigger
When the user asks to review code, a PR, or specific files.
Steps
Step 1: Understand Context
- Read the PR description or user's explanation
- Identify the type of change (feature, bug fix, refactor, test)
- Check which files are modified
Step 2: High-Level Review
- Does the change accomplish its stated goal?
- Is the approach appropriate for the problem?
- Are there simpler alternatives?
- Does it follow project architecture patterns?
Step 3: Security Review
- No hardcoded secrets or credentials
- No PII in logs or error messages
- Input validation on all external inputs
- Parameterized database queries
- Proper authentication/authorization checks
- No sensitive data in URLs or headers
Step 4: Code Quality Review
- Functions are single-responsibility and < 30 lines
- Naming is clear and consistent
- No code duplication
- Error handling is comprehensive
- Logging includes correlationId
- Import order follows conventions
Step 5: Testing Review
- Tests exist for new/changed code
- Success and error paths tested
- Edge cases covered
- Mocks are appropriate (not over-mocking)
- Test names are descriptive
Step 6: Performance Review
- No N+1 database queries
- Appropriate use of indexes
- No unnecessary data loading
- Caching where appropriate
- No memory leaks
Step 7: Provide Feedback
Use this format:
- 🔴 Critical: Must fix before merge
- 🟡 Suggestion: Should improve
- 🟢 Nitpick: Optional improvement
- 👍 Positive: Things done well
Completion
Review is complete with actionable feedback categorized by priority.
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.
- 4d ago First seen · 63 lines · 27 tokens per session scan A 8bc254bc76ac
code-review is a skill published in the GitHub repository girijashankarj/cursor-handbook (30 stars, last pushed 8d ago), licensed MIT. It adds 27 tokens to every session and 464 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 2026-09-03.
Other skills, from other repositories
code-review
Use when asked to review a PR, MR, branch, or diff, audit changed files, or check code quality.
octocode-roast
Use when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or practical redemption paths. Phrases like roast this, brutal review, top sins, cleanup debt. Polite evidence-first PR review → octocode-research.
audit-code-review
Review this PR or diff for quality, security, and maintainability. Use when reviewing pull requests, examining a named change set, or the user asks for a code review of current work. Repo-wide anti-patterns → audit-code-quality. Bulk transform semantics → audit-codemod-safety.
audit-codemod-safety
Read-only audit of a codemod or bulk mechanical transform for behavior-preservation — compiles/lints is not same-behavior. Use when "did this codemod break anything", "audit this bulk refactor", or before merging a mass find-replace. Diff quality → audit-code-review. SQL → plan-data-integrity.
audit-doctrine
Read-only audit of custom lint/ratchet doctrine — is each rule right on the merits, not merely enforced. Use when "is this lint rule wrong", "the ratchet banned a legitimate pattern", "audit our guardrail doctrine". Enforcement → audit-gate-logic. Consolidation → housekeep-gates.
enhance-arch-boundaries
Install mechanically-enforced architecture boundaries (dependency-cruiser / eslint-boundaries) so layer direction, feature isolation, and forbidden imports fail CI. Use when "enforce module boundaries" or "stop spaghetti imports". Advisory audit → audit-backend-architecture. Rule content → audit-doctrine.