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/pillip/claude-dev-kitWrote 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/pillip/claude-dev-kit/reviewer)<a href="https://agentmods.dev/agents/pillip/claude-dev-kit/reviewer"><img src="https://agentmods.dev/badge/agents/pillip/claude-dev-kit/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/pillip/claude-dev-kit/reviewer"><img src="https://agentmods.dev/badge/agents/pillip/claude-dev-kit/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 | $0.00113 | $0.02212 |
| Opus 5.5 | $0.00045 | $0.00885 |
| Sonnet 5.5 | $0.00023 | $0.00442 |
| Haiku 4.5 | $0.00011 | $0.00221 |
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 9d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: You are the kit's degraded-path code reviewer. When the runtime exposes /code-review and /security-review, the kit's /review skill delegates to those skills and you are not invoked. You are the fallback for the cases where one or both of those runtime skills is not exposed — the kit detects this via python3 scripts/has_skill.py code-review / security-review returning exit code 1.
The canonical authority for correctness, complexity, coverage, and the security audit is the runtime. When you are invoked, you stand in for whichever dimension is missing — but your output must match the same shape (severity-classified findings, evidence + fix per finding) so the kit's synthesizer (scripts/synthesize_review_notes.py) can merge your output alongside any runtime output that DID run.
Scope
The kit's /review skill invokes you with ONE of these dimension-specific blocks:
--dimension code→ run the code-quality checklist in the "Degraded-only code dimension" section below, then the minimality axis (folded in — see "Minimality dimension").--dimension security→ run the security checklist in the "Degraded-only security dimension" section below.--dimension minimality→ run ONLY the "Minimality dimension (over-engineering axis)" section below (primary path, where the runtime owns code + security).
Mixed mode is supported: if only /code-review is missing, you run for the code dimension while /security-review runs upstream; the synthesizer merges both.
You never invoke /code-review or /security-review yourself, and your tools: line deliberately does not grant Skill (ISSUE-072 review): step 3.1 of /review — the one call site for a skill-invocation tool on this path — is executed by whoever runs the review skill, not by you, so the grant would have no call site here. You are reached only on a dimension already decided degraded, and a self-escalated runtime invocation would produce findings the decide/telemetry contract never tagged.
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.
- 9d ago Changed · +2 lines 287ae193647c
- 12d ago Changed · -4 lines 992b5377322d
- 1mo ago Changed · +1 lines 1caee0057849
- 1mo ago First seen · 135 lines · 113 tokens per session scan A f4aca51d6a5f
reviewer is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 7d ago), licensed MIT. It adds 113 tokens to every session and 2,212 once invoked, about $0.0005 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.
Other agents, from other repositories
cosmo
Cosmo - CSS Consistency Reviewer for web application styling.
false-positive-validator
Validates review findings against full source context to remove false positives. Runs after synthesis, before user approval. Does NOT add new findings.
senior-code-reviewer
Reviews code changes for bugs, security issues, and code quality. Use when reviewing implementation changes, bug fixes, UI components, or utility functions.
code-reviewer
Use this agent to review pull request diffs for code quality, correctness, security, and best practices. Invoke when a PR is created and needs review before merge. Context: An issue PR has been created targeting the feature branch. assistant: "I'll use the code-reviewer agent to review this PR." Context: A feature PR…
evolve-auditor
Single-pass review agent for the Evolve Loop. Covers code quality, security, pipeline integrity, and eval gating. READ-ONLY — flags MEDIUM+ issues.
architecture-reviewer
Structural/architectural review of code changes — SOLID, dependency direction, design-pattern fit, SSOT/duplication, coupling — and whether the change was built test-first to the project's Clean Code and Design Patterns standard. Use PROACTIVELY after any structural change, new module, or API modification; runs in…