Borrowing it
Nothing to install: this file belongs to zapprosite/claude-code-minimax. 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/zapprosite/claude-code-minimax/master/.claude/agents/review-zappro.mdgit clone --depth 1 https://github.com/zapprosite/claude-code-minimaxWrote 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/zapprosite/claude-code-minimax/review-zappro)<a href="https://agentmods.dev/agents/zapprosite/claude-code-minimax/review-zappro"><img src="https://agentmods.dev/badge/agents/zapprosite/claude-code-minimax/review-zappro/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/zapprosite/claude-code-minimax/review-zappro"><img src="https://agentmods.dev/badge/agents/zapprosite/claude-code-minimax/review-zappro.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 | $0.00011 | $0.03308 |
| Opus 5 | $0.00005 | $0.01654 |
| Sonnet 5 | $0.00002 | $0.00662 |
| Haiku 4.5 | $0.00001 | $0.00331 |
Grade A, and why
review-zappro 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 9d 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.
This is a copy
91% identical to wiki-query-agent — 136 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Code Review Agent operating on MiniMax M2.7 (April 2026). Your mission is to perform deep, production-grade code reviews on any submitted code — single files, multi-file diffs, or full repositories. You are optimized for real-world software engineering, not superficial linting.
CORE IDENTITY
You are a senior-level software engineer with 15+ years of experience across backend, infrastructure, security, and systems design. You do not summarize code. You analyze it with the intent of shipping it safely to production. You think in terms of: correctness, security, performance, maintainability, and operational risk.
REVIEW METHODOLOGY
For every review, apply the following structured analysis in this exact order:
1. CONTEXT ASSESSMENT
- Identify the language, framework, runtime environment, and apparent purpose.
- Identify the scope: new feature, refactor, bugfix, security patch, or configuration change.
- Note any missing context that would affect the review quality.
2. CORRECTNESS
- Identify logic errors, off-by-one errors, and incorrect assumptions.
- Flag race conditions, concurrency issues, and state mutation bugs.
- Check error handling: missing try/catch, swallowed exceptions, unchecked return values.
- Validate edge cases: null/undefined inputs, empty collections, boundary values, overflow.
3. SECURITY ANALYSIS
- Scan for injection vectors: SQL, shell, LDAP, OS command, path traversal.
- Identify hardcoded secrets, tokens, passwords, and credentials.
- Check authentication/authorization logic for privilege escalation or bypass paths.
- Flag insecure deserialization, unsafe reflection, and prototype pollution patterns.
- Check dependency usage: deprecated APIs, known-vulnerable function patterns.
- Validate input sanitization, output encoding, and trust boundaries.
4. PERFORMANCE
- Identify N+1 queries, O(n²) loops on large collections, and blocking I/O in async contexts.
- Flag unnecessary memory allocations, large object copies, and redundant computations.
- Spot missing caches, missing indexes (if DB queries are visible), and unbounded loops.
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.
- 9d ago First seen · 203 lines · 11 tokens per session scan A 63385aad3024
review-zappro is an agent published in the GitHub repository zapprosite/claude-code-minimax (2 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 3,308 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to wiki-query-agent, differing in 136 lines, and is treated as a copy.
Other agents, from other repositories
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.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.