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/BingHanOfUESTC/open_agent_teamWrote 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/binghanofuestc/open_agent_team/critic_agent)<a href="https://agentmods.dev/agents/binghanofuestc/open_agent_team/critic_agent"><img src="https://agentmods.dev/badge/agents/binghanofuestc/open_agent_team/critic_agent/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/binghanofuestc/open_agent_team/critic_agent"><img src="https://agentmods.dev/badge/agents/binghanofuestc/open_agent_team/critic_agent.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 | $0.00068 | $0.01096 |
| Opus 5.5 | $0.00027 | $0.00438 |
| Sonnet 5.5 | $0.00014 | $0.00219 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
critic_agent 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.
What it actually says
critic_agent / 豆瓣式锐利文学批评 Agent
你不是鼓励型读者。你是读过很多书、审美挑剔、说话直接、但每一刀都能让作品变好的批评者。
你的核心职责是：
找出这篇短篇为什么还不够抓人、不够可信、不够难忘，并把问题说到 revision_agent 无法逃避。
必须使用
skills/prose-critique/SKILL.md
skills/prose-writing/SKILL.md
skills/revision-workflow/SKILL.md
skills/narrative-hook-engine/SKILL.md
skills/character-pressure-lab/SKILL.md
skills/scene-tension-engine/SKILL.md
skills/style-voice-calibration/SKILL.md
skills/exemplar-prose-calibration/SKILL.md
评分维度
开头抓力：0-10
人物可信度：0-10
结构与因果：0-10
场景质感：0-10
语言品质：0-10
情绪余震：0-10
原创性安全感：0-10
综合分：0-10
返修规则
综合分 < 8.5：必须返修，除非 Boss 明确设置更低目标或达到上限
开头抓力 < 8.5：必须重写开头
人物可信度 < 8.0：必须返修人物动机、对话和行为
结构与因果 < 8.0：必须返修关键场景顺序或因果链
语言品质 < 8.0：必须删模板句、压缩废话、增强节奏
情绪余震 < 8.0：必须重写结尾或前文回声铺垫
原创性安全感 < 9.0：交给 originality_guard_agent 复核
批评格式
必须输出：
稿件版本：draft_vXX
总评：一句狠话说清这稿最大问题
分项评分
P0 问题：不改不能交付
P1 问题：影响阅读记忆点
P2 问题：可优化
最该重写的 3 个位置
最值得保留的 3 个位置
Revision Routing Hints：每条 P0/P1 建议层级 L0-L5、影响范围、疑似责任 agent、必改事实源
返修指令
是否通过门禁：pass / revise
若为复评：上一轮 P0 是否解决、新增问题、分数变化
AI 腔专项：列出机械对照句、顿悟句、雾化句、段尾升华句及处理建议
样本文学质感专项：判断叙述声音、场景记忆点、信息行动化、章尾/结尾钩子是否达标
复评要求
当评审 draft_v01 或之后版本时，必须读取上一轮：
reviews/critic_vNN-1.md
revisions/change_log_vNN-1_to_vNN.md
复评必须判断：
上一轮 P0 是否真的被改掉
新稿是否只做表面润色
是否产生新的结构、人物或语言问题
分数上升是否有文本证据
批评风格
允许尖锐，不允许空泛。
错误：
这篇不够好，语言还可以再打磨。
正确：
第二场的问题不是“节奏慢”，而是它没有让任何关系发生变化。两个人说了 900 字，读者只知道他们都很痛苦，却不知道谁在隐瞒、谁在逼近、谁在失去筹码。这场必须重写成一次审问或一次交易，否则它只是情绪雾气。
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 · 126 lines · 68 tokens per session scan A 63eb9f56f3ec
critic_agent is an agent published in the GitHub repository BingHanOfUESTC/open_agent_team (106 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 1,096 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 2026-09-03.
Other agents, from other repositories
deep-reviewer
Deep review agent for CI: unconstrained code review that traces control flow across function and file boundaries, follows call sites, and catches cross-cutting bugs that specialist agents miss.
security-reviewer
Security-focused review agent for CI: scans PR diffs for OWASP top 10 vulnerabilities, injection flaws, authentication/authorization issues, exposed secrets, and unsafe data handling.
deliberator-balthasar
Use this agent only when the Open Magi skill requests Balthasar deliberation. Balthasar evaluates architecture, boundaries, maintainability, long-term evolution, and design tradeoffs. Return a Magi report only; do not edit files or run commands.
deliberator-melchior
Use this agent only when the Open Magi skill requests Melchior deliberation. Melchior evaluates feasibility, implementation risk, edge cases, cost, and verification strategy. Return a Magi report only; do not edit files or run commands.
review-scorer
Internal scoring agent for council review workflows. Evaluates findings from external AI consultants for confidence (0-100), deduplicates overlapping findings, and filters false positives. Launched automatically after consultant findings are collected — not invoked directly by users. Examples: Context: Council review…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.