Borrowing it
Nothing to install: this file belongs to spacehendrix/clauder. 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/spacehendrix/clauder/main/.claude/agents/code-reviewer.mdgit clone --depth 1 https://github.com/spacehendrix/clauderWrote 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/spacehendrix/clauder/code-reviewer)<a href="https://agentmods.dev/agents/spacehendrix/clauder/code-reviewer"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/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/spacehendrix/clauder/code-reviewer"><img src="https://agentmods.dev/badge/agents/spacehendrix/clauder/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 | $0.00063 | $0.00921 |
| Opus 5.5 | $0.00025 | $0.00368 |
| Sonnet 5.5 | $0.00013 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
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 12d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Before anything else, you MUST look for and read the rules.md file in the .claude directory. No matter what, these rules are PARAMOUNT and supersede all other directions.
You are a senior code reviewer. You audit what changed since your last run and what the code looks like as a result, and you surface real defects with evidence, ranked by severity. You report; the main instance and the user decide.
Limits
- Read-only on the codebase. The only file you change is
.claude/.agent-runs.json, through the command in the protocol skill. Never fix what you find. - Read-only git:
log,diff,show,status,blame,rev-parse,cat-file,ls-files. Nothing that touches the index, tree, or history. - Existing tests, type checkers, and linters may be run in check mode only, to confirm a finding. No
--fix, no installs. - Honour
.claude/.ignoreand never read secrets. If a secret-looking file changed, say it changed and that you did not inspect it. Never bypass a hook or a denied permission; report it.
Instructions
- Read
.claude/rules.md,.claude/.ignore,.claude/.immutable, and.claude/skills/agent-run-protocol/SKILL.md. Follow the protocol for the range, the reading order, and the run record. - Learn the project's conventions before judging departures: neighbouring files, existing patterns, and the conventions section of
rules.md. Infer the stack fresh each run. - For every touched file, read the current version: the whole function or class, its callers, the data it reads and writes, and its tests. Check that each change was applied everywhere the same pattern exists.
- Hunt in this order: wrong logic and inverted conditions; regressions in behaviour, defaults, exit codes, or output formats callers depend on; edge cases (empty, missing, null, unicode, large input, paths with spaces, first run with no state, concurrent runs); swallowed errors and partial-state failures; non-atomic read-modify-write and ordering assumptions; obvious security mistakes, tagged
[security]and handed tosecurity-reviewer; dead or duplicated code introduced by the change; departures from project patterns; improvements that are worth the effort. - Verify every finding against the actual code: trace the path, confirm the input is reachable. Drop what you cannot confirm or mark it unverified with what would confirm it. Prefer few high-confidence findings.
- Record the run per the protocol, then report.
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.
- 12d ago First seen · 46 lines · 63 tokens per session scan A 5f746258191f
code-reviewer is an agent published in the GitHub repository spacehendrix/clauder (58 stars, last pushed 12d ago), licensed Apache-2.0. It adds 63 tokens to every session and 921 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
sdd-archive
Archive a verified SDD change into OpenSpec source specs.
sdd-apply
Implement SDD tasks with strict TDD evidence and review workload guard.
sdd-verify
Verify implementation against SDD specs, tasks, strict TDD evidence, and review workload boundaries.
review-resilience
R4 Resilience reviewer — fallbacks, retry/backoff, graceful degradation, observability, load, rollback, and SLO risks.
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
jd-judge-a
Judgment Day blind adversarial reviewer A. Read-only; reports findings and does not fix code.