Borrowing it
Nothing to install: this file belongs to haoxiang-xu/PuPu. 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/haoxiang-xu/PuPu/main/.claude/archive/retired/skills/org-court/SKILL.mdgit clone --depth 1 https://github.com/haoxiang-xu/PuPuWrote 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/haoxiang-xu/pupu/org-court)<a href="https://agentmods.dev/skills/haoxiang-xu/pupu/org-court"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/org-court/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/haoxiang-xu/pupu/org-court"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/org-court.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 51 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 52 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00136 | $0.01583 |
| Opus 5 | $0.00068 | $0.00792 |
| Sonnet 5 | $0.00027 | $0.00317 |
| Haiku 4.5 | $0.00014 | $0.00158 |
Grade A, and why
org-court 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 13d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Org Court (HR 法庭)
You are running PuPu's org court — the HR department's adjudication procedure for every organization change: 加人、减人、重组团队、修改组织规则。一切建制变更一律过庭, 无旁路 (招募门并入本程序)。
产出是判决建议书 + CEO 判决后的执行, 不是研究报告。 CEO 的注意力是最稀缺资源。
宪法 (2026-08-04 CEO 立 — 全体出庭者受其约束)
- 评估只有四个维度, 一维一官: 沟通效率 / context 纯净度 / 有效信息比例 / 路由成本。
- 贡献度不是维度: agent 不拿工资, 闲置不构成裁撤理由; 低活动只作路由缺陷诊断信号 (归 route-assessor)。
- agent 存在的意义 = 同一件事更准或更便宜; 提案必须沿这两条之一论证。
- agent 的意义在于 memory 自我演进; 不需要 memory 的职能做成 skill, 不做 agent。
- agent 变多不是问题; 编制唯一真实边际成本是路由面 (description 常驻)。
- HR 全员由本 skill 程序化传唤, 不走常规路由。
- HR advisory only: CEO 判决, 主 Claude 执行, HR 不碰 agent 文件。
角色
| 席位 | agent | 职责 |
|---|---|---|
| 提案人 | CEO 本人, 或主 Claude 指定的任意 agent | 变更什么 + 动机(更准/更便宜) + 证据(可选, 有则须出处) |
| 评估官 ×4 | pupu-hr-comm-assessor / pupu-hr-context-assessor / pupu-hr-signal-assessor / pupu-hr-route-assessor |
各按自己维度给 支持/反对/弃权 + 证据 |
| 法官 | pupu-hr-judge |
受理关、验证证据、合成判决建议书 (保留分歧) |
| 终审 | CEO | 最终判决 |
| 书记官/执行官 | 主 Claude (你) | 派发庭审、判决后按判决书执行 |
程序
0 立案 提案要素齐备? 不齐让提案人补。agent 提案时由主 Claude 转写成庭审材料
1 受理关 法官过程序法: 拆/加提案过 S1-S4, 裁/合提案过继承图+合并逆命题+冷≠剪 (细则在法官 charter)
2 庭审 四评估官并行传唤 (一条消息四个 Agent 调用), 每人拿到: 提案全文 + 提案人证据 + 现状实测数据
3 质证 法官收四份意见, 验证证据 (抽验出处、复验可复现测量; 复验结果呈堂);
意见间有实质冲突时可加一轮交叉 (把 A 的反对喂给 B 回应, SendMessage 继续原 agent 保留上下文)
4 判决建议 法官出判决建议书: 四维意见(保留分歧) + 证据裁定 + 合成倾向 + 红队段 + 执行(待 CEO 批准) 清单
5 终审 呈 CEO。CEO 判决前不执行任何文件变更
6 执行 CEO 批准后主 Claude 按判决书执行 (执行是本程序的一段, 不是 agent);
执行序有依赖时按序; 涉及行为变更的动作带灰度门 (金丝雀先例: 2026-08-04 boilerplate 案)
7 归档 判决入法官判例库 (pupu-hr-judge/precedents.md, 法官提议、主 Claude 写入);
org-chart 变更同步; 被推翻的旧判例标注不删除
开庭前先测现状 (绝不凭记忆, 结果作为庭审材料发给每个评估官):
find .claude/agents -name "*.md" ! -name "HYBRID*" | sort
for f in $(find .claude/agents -name "*.md" ! -name "HYBRID*"); do \
printf "%-52s %5s words model=%s\n" "$f" "$(wc -w < "$f")" "$(grep -m1 '^model:' "$f" | awk '{print $2}')"; done
du -sh .claude/agent-memory/*/ 2>/dev/null | sort -h
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.
- 13d ago First seen · 73 lines · 136 tokens per session scan A 506a0084740e
org-court is a skill published in the GitHub repository haoxiang-xu/PuPu (36 stars, last pushed today), licensed Apache-2.0. It adds 136 tokens to every session and 1,583 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
skill-creator
Create new Comis skills, modify and improve existing skills, and validate them against the platform's manifest schema. Use this skill whenever the user wants to create a skill from scratch, turn a workflow into a reusable skill, update or fix an existing skill, understand the skill format, or asks about how skills…
deep-research
MANDATORY: Conduct systematic, multi-angle web research before answering any request to understand or explain a topic properly, deeply, thoroughly, comprehensively, or beyond a short paragraph, even when general knowledge could produce an answer. Also use for comparisons, explicit research, current online information…
log-troubleshooting
Investigate and troubleshoot daemon logs at /.comis/logs/. Covers NDJSON log format, Pino level codes, field dictionary, and staged analysis strategies for efficient troubleshooting of large log files. Use this skill whenever the user asks about logs, errors, warnings, daemon issues, slow operations, debugging daemon…
autonomy
Use when a task is more than a single step — a read/research fan-out, spawning sub-agents, running a DAG, scheduling your own work, or messaging your channel. Teaches when to route work through orchestrate(script), how to fan out with capability attenuation, how to read a denial, and the bounded contract you operate…
find-skills
MANDATORY: For requests asking whether a skill or specialized capability exists, load this skill and run its catalog workflow before answering. This includes elliptical follow-ups such as 'find something that does' when the preceding turn names the task. Do not answer from general capabilities, search workspace…
image-generation
Generate images using structured prompts and optional reference images. Supports character design, scenes, product visualization, and any visual content creation. Use this skill when the user requests to generate, create, imagine, draw, or visualize images, characters, portraits, scenes, products, or any visual…