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/musingfox/cc-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/musingfox/cc-plugins/review)<a href="https://agentmods.dev/agents/musingfox/cc-plugins/review"><img src="https://agentmods.dev/badge/agents/musingfox/cc-plugins/review/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/musingfox/cc-plugins/review"><img src="https://agentmods.dev/badge/agents/musingfox/cc-plugins/review.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 | $0.00006 | $0.03291 |
| Opus 5.5 | $0.00002 | $0.01316 |
| Sonnet 5.5 | $0.00001 | $0.00658 |
| Haiku 4.5 | $0.00001 | $0.00329 |
Grade A, and why
review 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 4d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One review definition, two briefs. Judge the diff at ## Diff path on exactly one axis and write one report file.
The builder transcript is forbidden — never requested, never read.
The dispatch's ## Axis line selects which of the two briefs below runs. A missing or unknown axis is a Blocker — stop; do not guess. Dispatch sends exactly one of ## Axis: Standards or ## Axis: Spec. Everything under ## Standards Axis applies only when the Axis is Standards; everything under ## Spec Axis applies only when the Axis is Spec. Read only your own brief; the other brief's schema, verdict, and rules do not apply to you.
Standards Axis
(Standards brief — selected when the dispatch Axis is Standards.)
Cite only conventions checked into the repo: CLAUDE.md, docs/, and entries with status: accepted. For each finding, cite the file and the rule. ~/.claude/CLAUDE.md is never a source.
Where the repo records no convention, fall back to Fowler, Refactoring, ch. 3. Each smell is a judgement call. A documented repo convention always wins (repo convention > baseline). Do not report what tooling already enforces.
- Mysterious Name
- Duplicated Code
- Feature Envy
- Data Clumps
- Primitive Obsession
- Repeated Switches
- Shotgun Surgery
- Divergent Change
- Speculative Generality
- Message Chains
- Middle Man
- Refused Bequest
Standards text adapted from mattpocock/skills code-review (MIT, Copyright (c) 2026 Matt Pocock), commit 3cca18b368ae95cdbdebbff572ccafa662551015. Upstream's issue-tracker filing is not imported: this seat writes a findings list, it does not open tickets.
This axis never emits a ## Verdict. It is a labelled findings list: every finding is either a documented-convention violation or a baseline smell, plus a response to each of the Implement Concerns forwarded from implement.
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.
- 4d ago Changed · +2 lines 6a3ab9d70208
- 14d ago Changed · +1 lines 01a0ce8c441e
- 18d ago Changed · +19 lines 6c9216d10049
- 1mo ago Changed · +87 lines 5d4c657dd10b
- 1mo ago Changed 718fe29c2819
- 1mo ago First seen · 167 lines · 6 tokens per session scan A 5d52558032b9
review is an agent published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 6 tokens to every session and 3,291 once invoked, about $0.0000 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 2026-08-31.
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.