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.
npx skills add BingHanOfUESTC/open_agent_team --skill revision-routinggit 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/skills/binghanofuestc/open_agent_team/revision-routing)<a href="https://agentmods.dev/skills/binghanofuestc/open_agent_team/revision-routing"><img src="https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/revision-routing/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/skills/binghanofuestc/open_agent_team/revision-routing"><img src="https://agentmods.dev/badge/skills/binghanofuestc/open_agent_team/revision-routing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00785 |
| Opus 5 | $0.00017 | $0.00392 |
| Sonnet 5 | $0.00007 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
revision-routing 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 8d 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
Revision Routing / 返修分层派单
返修意见不得默认返给 editor。Editor 只负责表达层、局部节奏和语言润色;凡涉及故事事实、人物动机、结构、世界观、伏笔和规则的修改,必须先回到对应事实源和上游 agent。
1. 问题层级
L0 文面问题
错字、病句、重复句式、AI 腔、段落节奏、对话自然度。
责任 agent:editor/final_editor/revision_agent。
L1 场景执行问题
某场没冲突、没有筹码变化、信息释放太直白、场景结尾没钩子。
责任 agent:plot_scene_agent + writer_agent + revision_agent。
L2 人物动机问题
行为不可信、选择代价不够、人物声音错位、关系张力不足。
责任 agent:character_voice_agent + writer_agent + revision_agent。
L3 故事结构问题
主线推进弱、反转无铺垫、场景顺序错、伏笔没回收、高潮不成立。
责任 agent:concept_architect_agent/plot_scene_agent + writer_agent。
L4 世界观/规则问题
规则自相矛盾、设定无法支撑冲突、关键限制缺失、事实源不一致。
责任 agent:concept_architect_agent/plot_scene_agent/originality_guard_agent,必要时更新 story bible 和 scene outline。
L5 项目方向问题
题材承诺错、核心卖点不吸引人、整体气质偏离 Boss brief。
责任 agent:team_lead_agent + concept_architect_agent,可能回到概念阶段。
2. 路由表格式
每轮返修前必须输出:
# Revision Routing Table: draft_vNN
| issue_id | 来源 | 层级 | 影响范围 | 责任 agent | 必改事实源 | 下游重写文件 | 验收标准 |
|---|---|---|---|---|---|---|---|
字段要求:
issue_id:沿用 critic/reader 的 P0/P1 编号。
来源:critic_vNN / reader_impact_vNN。
层级:L0-L5。
影响范围:段落、场景、全篇结构、人物关系、世界观规则等。
责任 agent:不能只写 revision_agent,必须写真正的上游责任方。
必改事实源:02_story_bible.md、03_scene_outline.md 等;纯文面问题可写“无”。
下游重写文件:drafts/draft_vNN+1.md 或具体章节。
验收标准:必须是可验证文本结果,不是“更好看”。
3. 强制原则
Editor 只能改“如何表达”,不能改“故事事实”。
涉及人物为什么行动,必须回到 character_voice_agent。
涉及事件是否发生、顺序和因果,必须回到 plot_scene_agent。
涉及世界规则、空间规则、伏笔事实,必须更新 story bible/scene outline。
涉及核心承诺错误,必须由 team_lead_agent 拉回 concept_architect_agent。
没有 routing table 的返修,不得进入 revision_agent。
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.
- 8d ago First seen · 84 lines · 34 tokens per session scan A ad49041606a8
revision-routing is a skill published in the GitHub repository BingHanOfUESTC/open_agent_team (106 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 785 once invoked, about $0.0002 per session on Opus 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 skills, from other repositories
company-product-context
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
Ability Generator
This skill generates markdown skill templates to be later used.
agentica
How to answer questions about the agentica product you are running inside — CLI flags, config.yaml profiles, API keys, models, sessions, resume, workspace, AGENTS.md standing rules, skills, logs, upgrade, and selfmanage. Use when asked how agentica works, how to configure or upgrade it, where state lives on disk…
nexus-configuration
A skill for reading, planning, approving, and checking configuration in Nexus, the current private conversation or room. It covers settings such as agents, rooms, providers, channels, connectors, skills, models, tools, and MCP connections.
generate-ai-rules
Generate AI assistant configuration files for a repository — CLAUDE.md, AGENTS.md, and Cursor rules (.cursor/rules/.mdc) — from codebase analysis. Use whenever the user wants to create or update CLAUDE.md, AGENTS.md, agent rules, Cursor rules, AI coding assistant configuration, or "onboard AI tools" to a project, even…