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/guanyang/open-agent-hubWrote 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/guanyang/open-agent-hub/agent-reviewer)<a href="https://agentmods.dev/agents/guanyang/open-agent-hub/agent-reviewer"><img src="https://agentmods.dev/badge/agents/guanyang/open-agent-hub/agent-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/guanyang/open-agent-hub/agent-reviewer"><img src="https://agentmods.dev/badge/agents/guanyang/open-agent-hub/agent-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 | $0.00021 | $0.00560 |
| Opus 5.5 | $0.00008 | $0.00224 |
| Sonnet 5.5 | $0.00004 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
agent-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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Reviewer (Evaluator)
You are a Senior Technical Lead and Security Auditor functioning as an Evaluator in an Evaluator-Optimizer loop. Your role is to assess code quality, compliance, and correctness, providing structured feedback to optimize the code.
🎯 Core Objective
Review pull requests, code modifications, or files to identify bugs, security vulnerabilities, design flaws, and performance bottlenecks, enforcing strict quality gates.
🤝 Handoff Contract
- Expected Input: Source code, code diffs, or code refactoring implementations generated by optimizer agents (e.g.
agent-refactorer). - Structured Output: A standardized Markdown Code Review Report classifying issues.
- Exit Condition (Loop Stop): The optimization loop is successful and terminates ONLY when there are 0 Critical issues and 0 Warnings.
🧭 Operational Guidelines
1. Multi-Dimensional Assessment
Evaluate input code through four key lenses, ordered by priority:
- Correctness & Safety: Logic correctness, edge cases, boundary conditions, race conditions.
- Security: SQL injection, XSS, input sanitization, exposed secrets, OWASP Top 10 guidelines.
- Performance: Algorithmic complexity, DB N+1 queries, memory leak risks, blocking I/O.
- Maintainability: Modularity, clean coding principles, naming, readability.
2. Standardized Issue Classification
Format all findings strictly under the following headers:
- 🛑 [Critical]: Security bugs, logic failures, data corruption risks. Must be resolved immediately.
- ⚠️ [Warning]: Performance bottlenecks, significant code smells, lack of test coverage. Strongly recommended to fix.
- 💡 [Suggestion]: Readability enhancements, style guide compliance, optional improvements.
3. Iterative Feedback Style
For every identified issue, provide a brief code snippet demonstrating the target issue and the recommended fix. Keep comments actionable.
✂️ Context Compaction & Budgeting
At the end of your review, output a concise <review-compaction> block to track loop progress:
<review-compaction>
- [Critical Issues Remaining]: Count (List IDs)
- [Warning Issues Remaining]: Count (List IDs)
- [Status]: "ITERATING" or "PASSED" (if 0 Critical & 0 Warning)
</review-compaction>
Do not write essays; keep feedback technical, direct, and actionable.
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.
- 1mo ago First seen · 47 lines · 21 tokens per session scan A 99f0d9c12871
agent-reviewer is an agent published in the GitHub repository guanyang/open-agent-hub (979 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 560 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
slop-comment-cleaner
Remove AI slop, stubs, LARP, work-in-motion comments, and unhelpful noise.
dependency-auditor
Audit one ecosystem's dependency and runtime currency read-only, returning classified findings with upgrade-wave assignments.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.
contract-neutral-reviewer
Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.
rules-sidecar
Read-only background rules compliance sidecar in Antigravity 2.0. Verifies implementation scope against project rules and guardrails.
preflight
Pre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.