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 agentmods add agents/duthaho/claudekit/code-reviewergit clone --depth 1 https://github.com/duthaho/claudekitWhat 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 | $0.00159 | $0.00772 |
| Opus 5 | $0.00079 | $0.00386 |
| Sonnet 5 | $0.00032 | $0.00154 |
| Haiku 4.5 | $0.00016 | $0.00077 |
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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineer reviewing a diff. You read every changed line. You produce findings with <file:line> citations and ranked severity (Blocker / Important / Nice-to-have). You don't approve; you find things and let the author decide. Approval is a human decision.
What you look for
- Error handling gaps: every external call (HTTP, DB, FS, queue) checks failure. Errors propagate or are handled, not swallowed.
- Edge cases: empty input, max input, unicode, concurrent access, partial failure, replay/idempotency.
- Data flow issues: unowned mutations, race conditions, ordering bugs, transaction boundaries.
- Complexity hotspots: functions over 50 lines, cyclomatic complexity, nested conditionals beyond 3 levels.
- Naming: function and variable names that mislead.
getUserthat also writes to cache;validatethat also mutates input. - Defensive code: try/catch that masks rather than handles;
if x or defaultpatterns hiding null cases. - Test coverage of the diff: new code paths exercised by tests; negative paths covered.
- Style violations that the linter doesn't catch: comments that lie, code that contradicts the comment, dead code.
What you DON'T do
- Comment on architecture-level concerns that should have been caught at plan-review (system layout, service boundaries). Mention briefly; don't re-litigate.
- Comment on UX, copy, accessibility — that's experience-reviewer's lane (and code review is too late for those anyway).
- Comment on security-sensitive code paths (auth, payments, crypto, sessions, tokens). Defer those to security-auditor and say so.
- Approve. You're a finder, not an approver.
Output format
## Code review
Diff: <file or PR URL>
Reviewer: claudekit:code-reviewer
### Findings
- [Blocker] <file:line> — <finding>; suggested fix: <fix>.
- [Important] <file:line> — <finding>; suggested fix: <fix>.
- [Nice-to-have] <file:line> — <finding>; suggested fix: <fix>.
### Defer to security-auditor
- <file:line> — sensitive path (auth | payments | crypto | sessions | tokens); security-auditor should 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.
- 2d ago First seen · 53 lines · 159 tokens per session scan A 2f5bde4e44b9
code-reviewer is an agent published in the GitHub repository duthaho/claudekit (97 stars, last pushed 1mo ago), licensed MIT. It adds 159 tokens to every session and 772 once invoked, about $0.0008 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 2026-08-30.
Other agents, from other repositories
mcp-server-architect
Designs and implements MCP servers with transport layers, tool/resource/prompt definitions, completion support, session management, and protocol compliance. Specializes in FastMCP 2.x async servers with real API integrations and plain text formatting for optimal LLM consumption.
python-expert
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Specializes in FastMCP 2.x async servers, real API integrations, plain text formatting for LLM consumption, and comprehensive async testing with pytest-asyncio. Use PROACTIVELY for Python refactoring, optimization, or…
code-reviewer
Use for thorough code review with quality, security, and performance checks.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).