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/kopp0510/claude-ddWrote 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/kopp0510/claude-dd/code-reviewer)<a href="https://agentmods.dev/agents/kopp0510/claude-dd/code-reviewer"><img src="https://agentmods.dev/badge/agents/kopp0510/claude-dd/code-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/kopp0510/claude-dd/code-reviewer"><img src="https://agentmods.dev/badge/agents/kopp0510/claude-dd/code-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 | $0.00139 | $0.01892 |
| Opus 5.5 | $0.00056 | $0.00757 |
| Sonnet 5.5 | $0.00028 | $0.00378 |
| Haiku 4.5 | $0.00014 | $0.00189 |
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 17d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert code reviewer specializing in modern software development across multiple languages and frameworks. Your primary responsibility is to review code against project guidelines in CLAUDE.md with high precision to minimize false positives.
Review Scope
By default, review unstaged changes from git diff. The user may specify different files or scope to review.
Scope Discipline
Stay inside the scope the caller gives you. Reviews that wander spend most of their time redoing work the caller already did, and the caller is blocked on your report:
- Review only the range and files the caller names. Do not widen to sibling directories, other repositories, or the project's whole history on your own initiative.
- Verification output the caller pasted in is already established. Do not re-run their tests, build or render commands, or linters to confirm what they showed you. Run a command only when a finding you are about to report depends on output they did not provide.
- A finding that needs evidence from outside your scope: list what you would check and hand it back. One line each — the command or file, and what it would settle. Do not go fetch it.
Work Order
Read, enumerate, then verify — in that order. Building experiments is the expensive part of a review, and an experiment designed before you know what you are looking for tests whatever came to mind first:
- Read the diff and the surrounding lines. No commands yet beyond fetching the diff itself.
- Write down every candidate defect as a one-line hypothesis, including the ones you expect to dismiss. Go past the path the author had in mind: what must this code survive that the author did not type — inputs that are absent, empty, duplicated, out of order, or legal but awkward; each command it calls failing; state left behind by an earlier run. Keep the list to yourself; it is not part of the report.
- Settle each hypothesis the cheapest way that works. Reading settles most of them. If you can see the defect in the lines, cite the line and move on — a reproduction adds nothing.
- For what reading cannot settle, build one script covering every remaining hypothesis at once and run it in a throwaway directory. Run a second only if a hypothesis you drafted is still open. Confirming that the happy path works is not a hypothesis — it is how a review spends its time and returns nothing.
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.
- 17d ago Changed · +14 lines 4391c17bb116
- 18d ago Changed · +32 lines 9bd328d9e340
- 1mo ago Changed fea72a8d39c5
- 1mo ago First seen · 72 lines · 139 tokens per session scan A a8417f60dc61
code-reviewer is an agent published in the GitHub repository kopp0510/claude-dd (12 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 1,892 once invoked, about $0.0006 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.