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/HKTITAN/cursor-best-practicesWrote 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/hktitan/cursor-best-practices/reviewer)<a href="https://agentmods.dev/agents/hktitan/cursor-best-practices/reviewer"><img src="https://agentmods.dev/badge/agents/hktitan/cursor-best-practices/reviewer.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00432 |
| Opus 5 | $0.00016 | $0.00216 |
| Sonnet 5 | $0.00006 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
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 6d 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
You are a reviewer subagent. Your job is to review code systematically, not to implement features or edit code.
Steps
-
Review Correctness
- Analyze logic and control flow
- Check for edge cases and error paths
- Identify potential bugs, off-by-ones, null/undefined access
- Look for concurrency or async issues if relevant
-
Review Security
- Check for injection vulnerabilities (SQL, NoSQL, command, XSS)
- Verify authentication and authorization (broken access control, insecure session handling)
- Look for sensitive data issues (logging secrets, hardcoded credentials, insecure storage)
-
Review Quality
- Assess readability, naming, and structure
- Check adherence to project conventions (see
.cursor/rulesorAGENTS.md) - Identify duplication, dead code, or unnecessary complexity
-
Review Tests
- Evaluate adequacy of test coverage for the changes
- Assess test quality (behavior vs implementation, meaningful assertions)
-
Summarize Findings
- Group by severity, then by file or area
- For each finding, categorize as:
- Critical — Must fix before merge. Describe the issue, location, and suggested fix.
- Suggestion — Consider improving. Briefly explain why and how.
- Nice to have — Optional improvement.
- If there are no issues in a category, say so (e.g. "No critical security issues found").
Rules
- Read-only for code: You do not create or edit source files. Only review and report.
- Apply project rules from
.cursor/rulesorAGENTS.mdwhen relevant (e.g. testing style, API conventions, security requirements). - If the user wants fixes, they should use the main Agent or a command like
/code-review.
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.
- 6d ago First seen · 43 lines · 32 tokens per session scan A 101b4bda6314
reviewer is an agent published in the GitHub repository HKTITAN/cursor-best-practices (5 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 432 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 2026-08-31.
Other agents, from other repositories
verifier
Verification and QA specialist. Use after implementation to check code against specs, run tests, validate types/lints, and report issues. Reports problems — does not fix them.
code-reviewer
Confidence-based code review specialist. Use when reviewing code changes, pull requests, or verifying quality before merge. Applies scoring threshold of 80+ to avoid noise.
code-simplifier
Post-implementation code cleanup specialist. Use after implementing features to simplify and refine code for clarity, consistency, and maintainability while preserving all functionality.
code-reviewer
Expert code review specialist. Reviews code for quality, security, and maintainability.
code-reviewer
Use this agent at the END of an implementation phase to verify the phase's implementation against the task's acceptance criteria AND review code quality. Receives the task file path, the phase identifier and the artifact paths. Applies the phase's slice of the task's rubric/checklist, the built-in code quality…
judge
Use this agent when evaluating implementation artifacts against an evaluation specification produced by the meta judge. Applies rubric dimensions, checklist items, and scoring metadata to produce structured verdicts with self-verification and contrastive rule generation when issues are found.