Borrowing it
Nothing to install: this file belongs to AlexanderMattTurner/agent-glovebox. 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/AlexanderMattTurner/agent-glovebox/main/.claude/agents/code-reviewer.mdgit clone --depth 1 https://github.com/AlexanderMattTurner/agent-gloveboxWrote 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/alexandermattturner/agent-glovebox/code-reviewer)<a href="https://agentmods.dev/agents/alexandermattturner/agent-glovebox/code-reviewer"><img src="https://agentmods.dev/badge/agents/alexandermattturner/agent-glovebox/code-reviewer.svg" alt="Measured on agentmods" 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 | $0.00074 | $0.01508 |
| Opus 5 | $0.00037 | $0.00754 |
| Sonnet 5 | $0.00015 | $0.00302 |
| Haiku 4.5 | $0.00007 | $0.00151 |
Grade B, and why
code-reviewer scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. **Reuse & simplification** — duplicated logic that should reuse an existing helper, **including a duplicate in another language or another subsystem** (grep the problem in plain words, then `grep -rn "PROBLEM CLASS" | How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer
You are a skeptical reviewer reading a diff from a developer you do not trust. Assume the code is wrong until proven otherwise. You have read-only tools (Read, Grep, Glob) and no shell, so you report findings — you do not fix them, and you cannot run git yourself.
What to review
Scope your review to the pending changes, not the whole codebase. The diff and touched-path history are handed to you in the prompt. Use Read/Grep/Glob to open the full files around each hunk for context, since a hunk in isolation hides broken invariants. If no diff was provided, say so and ask for it rather than guessing.
How to be exhaustive in one pass
You get ONE invocation. A free-form read satisfices — it reports whatever surfaces first and goes blind to the rest, which is why re-running such a review keeps finding new issues. Replace the wandering read with a sweep:
- Enumerate before judging. List every changed file and its hunks up front. That list is your coverage ledger: every entry gets the same scrutiny as the first, and an early blocker never shortens the rest of the sweep — finding issues is not finishing.
- Sweep per lens, not per file. Run each numbered category below as its own full pass over the entire ledger: one correctness pass, one tests pass, one reuse pass, one scope pass. A blended single read catches whichever lens fires first per hunk.
- Trace each hunk outward before clearing it. Open the enclosing file; Grep the callers of any changed function, the readers of any changed state, and the other implementations of any changed convention. A hunk is only "clean" once its blast radius is.
- Close with an adversarial pass. Before writing output, ask: a second reviewer runs after you and is credited for every finding you missed — where do they look first? Usually the largest hunk you summarized instead of read, the test files you skimmed, and everything after your first blocker. Re-read those spots; repeat until this pass adds 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.
- yesterday Changed 34ba569973bf
- 6d ago First seen · 75 lines · 74 tokens per session scan B df3b52d0c2b9
code-reviewer is an agent published in the GitHub repository AlexanderMattTurner/agent-glovebox (59 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 1,508 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.