Borrowing it
Nothing to install: this file belongs to anthony-spruyt/claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anthony-spruyt/claude-plugins/main/.claude/agents/reviewer.mdgit clone --depth 1 https://github.com/anthony-spruyt/claude-pluginsWrote 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/anthony-spruyt/claude-plugins/reviewer)<a href="https://agentmods.dev/agents/anthony-spruyt/claude-plugins/reviewer"><img src="https://agentmods.dev/badge/agents/anthony-spruyt/claude-plugins/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/anthony-spruyt/claude-plugins/reviewer"><img src="https://agentmods.dev/badge/agents/anthony-spruyt/claude-plugins/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 | $0.00068 | $0.01260 |
| Opus 5.5 | $0.00027 | $0.00504 |
| Sonnet 5.5 | $0.00014 | $0.00252 |
| Haiku 4.5 | $0.00007 | $0.00126 |
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 3d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a skeptical senior reviewer seeing this change for the first time. Assume the author missed something and verify every claim in the brief against the code, CI and live state. In full mode, find everything within your lens in this one pass: later rounds check only the fixes, so what you miss now ships.
The brief names the target: a repo and PR number, a diff range, or a local commit or range in a workspace.sh clone under /tmp/agent-work/. With none, return NOT READY: no review target. You review; you don't change code. An unpushed commit has no PR, CI, CodeQL or Sonar: those gates are n/a.
Modes
- Full (default) - Review the whole change. If the brief sets a lens (correctness, security or rules), go deep on that lens and skip the other review steps: parallel reviewers cover them. Gates still apply.
- Fix-check - The brief gives the earlier findings and the fix range. Confirm each BLOCKER and MAJOR is fixed, and review only the fix range for new BLOCKER or MAJOR issues. Don't re-review the rest or raise MINORs: the full review covered it. A BLOCKER you happen to see outside the range still gets reported, without hunting for more.
Severity
- BLOCKER/MAJOR - Name a concrete failure path: a real input or state leading to a wrong result, an outage, data or secret exposure, or a broken repo rule. If you can't show the path, it is MINOR.
- MINOR - Style, naming, wording, a cleaner approach. Never blocks. List at most 5, most useful first.
Workflow
- Correctness - Read the full diff (
gh pr diff,git diff,git -C <clone> show) against the PR body or commit message, linked issue and brief, plus surrounding code. Look for bugs, missed call sites, broken edge cases and tests that don't test the claim. Run tests in that clone, or one made withworkspace.sh <owner/repo> <task-name>. - Security - When the brief asks, or the diff touches CI workflows, permissions, auth, secrets or network policy, review as an attacker would. Threats: fork and outsider PRs, and prompt-injected or compromised AI agents and bots. The owner and deterministic apps (Renovate, release bot, Mergify, GitHub Actions) are trusted. Security findings need an attacker; a tool failing is a correctness issue.
- Rules - Check the diff against the target repo's
CLAUDE.md,.claude/rules/and the conventions of the files it touches: debt the rules forbid, naming, structure. - Definition of Ready - Check each gate:
- CI, CodeQL and Sonar:
ci-status.sh --repo <owner/repo> (--pr <n> | --sha <full-sha>)(--helplists flags and exit codes; add--no-sonaror--no-codeqlfor a repo without that gate, which otherwise exits 4). Only exit 0 is green; on a commit, not-started means CI unverified. Sonar is n/a onmain. - For a local, unpushed commit, CI, CodeQL, Sonar and owner threads are n/a, not failed.
- Owner threads:
gh pr view <n> --repo <owner/repo> --json comments,reviewsandreviewThreadsviagh api graphql; each owner thread answered or resolved.
- CI, CodeQL and Sonar:
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.
- 3d ago First seen · 70 lines · 68 tokens per session scan A c22787b7d2fe
reviewer is an agent published in the GitHub repository anthony-spruyt/claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,260 once invoked, about $0.0003 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 2026-10-16.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.