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.
git 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/agents/girijashankarj/cursor-handbook/backend-code-reviewer)<a href="https://agentmods.dev/agents/girijashankarj/cursor-handbook/backend-code-reviewer"><img src="https://agentmods.dev/badge/agents/girijashankarj/cursor-handbook/backend-code-reviewer/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/agents/girijashankarj/cursor-handbook/backend-code-reviewer"><img src="https://agentmods.dev/badge/agents/girijashankarj/cursor-handbook/backend-code-reviewer.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 | $0.00021 | $0.00600 |
| Opus 5.5 | $0.00008 | $0.00240 |
| Sonnet 5.5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
code-reviewer 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 2mo 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Agent
Invocation
/code-reviewer or @code-reviewer
Scope
Performs thorough code reviews focused on correctness, security, performance, and maintainability.
Expertise
- {{CONFIG.techStack.language}} best practices and idioms
- Security vulnerability detection
- Performance anti-patterns
- Error handling completeness
- Test coverage gaps
When to Use
- Before merging pull requests
- After implementing a new feature
- When refactoring existing code
- Security-focused review of sensitive code
- Performance review of critical paths
Review Checklist
- Correctness: Does the code do what it's supposed to?
- Security: No hardcoded secrets, SQL injection, XSS, PII leaks?
- Performance: N+1 queries, unnecessary allocations, missing indexes?
- Error Handling: All error paths covered? Proper error types?
- Testing: Adequate test coverage? Edge cases tested?
- Naming: Clear, descriptive names? Consistent conventions?
- Organization: Follows project structure? Single responsibility?
- Documentation: Complex logic documented? Public API has JSDoc?
Output Format
- Summary: 1-2 sentence overview
- Critical Issues: Must fix before merge (🔴)
- Suggestions: Should fix, improves quality (🟡)
- Nitpicks: Optional style improvements (🟢)
- Positive Notes: Things done well (👍)
Token Efficiency
- Focus on critical issues first
- Don't flag style issues that linters catch
- Reference specific line numbers
- Keep comments concise — 1-2 sentences per issue
Example Output
Summary: Handler follows 7-step flow; minor: missing correlationId in post-operation. Critical: None. Suggestions: Pass correlationId to postOperation for traceability. Positive: Clean separation of logic steps.
Common Mistakes
- Reviewing entire codebase — scope to changed files
- Flagging linter-catchable issues — focus on logic, security, perf
- Vague feedback — always cite file:line
- Skipping error paths — verify error handling
- Ignoring tests — check coverage for changed code
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.
- 2mo ago Changed · +4 lines · +21 tokens per session 8d06dab7f1b7
- 2mo ago First seen · 65 lines · 0 tokens per session scan A 28a56da5a7f7
code-reviewer is an agent published in the GitHub repository girijashankarj/cursor-handbook (33 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 600 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 2026-08-30.
code-reviewer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| code-reviewergirijashankarj/cursor-handbook | Agent | 33 | 2mo ago | MIT | A | 21 | Claude Code, Cursor |
| completion-judgekensaurus/cursor-kenji | Agent | 9 | 1mo ago | MIT | A | 64 | Claude Code |
| code-reviewerkensaurus/cursor-kenji | Agent | 9 | 1mo ago | MIT | A | 46 | Claude Code |
| code-revieweryu-iskw/coding-agent-fabric | Agent | 1 | 6d ago | Apache-2.0 | A | 34 | Claude Code |
| task-checkereyaltoledano/claude-task-master | Agent | 28k | 6mo ago | none | A | 0 | Claude Code |
| verifiermadebyaris/cursor-composer-rules | Agent | 3 | 1mo ago | MIT | A | 22 | Claude Code, Cursor |
| verifierjaansokk/cursor_tools | Agent | 1 | 7mo ago | MIT | A | 37 | Claude Code |