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 LWTlong/aida --skill aida-governgit clone --depth 1 https://github.com/LWTlong/aidaWrote 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/lwtlong/aida/aida-govern)<a href="https://agentmods.dev/skills/lwtlong/aida/aida-govern"><img src="https://agentmods.dev/badge/skills/lwtlong/aida/aida-govern.svg" alt="Measured on agentmods" 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 | $0.00053 | $0.03615 |
| Opus 5 | $0.00026 | $0.01808 |
| Sonnet 5 | $0.00011 | $0.00723 |
| Haiku 4.5 | $0.00005 | $0.00362 |
Grade A, and why
aida-govern 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.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDA Govern
Goal
一次连贯的 AI 资产治理流程。一站式 —— 不要把子问题推给其他 skill,所有类别的清理都在这一次流程里给出方案。
Safety Rules
- 先分析,不写文件。
- 用 AskUserQuestion 让用户明确确认后再落盘。
- 所有写操作走
aida_apply_governance(journal 内建,出错用aida_undo一键回滚)。 - 分组要少、要有意义,不要一条规则一个动作。
- 绝不 punt:识别出的每一类问题都必须给出计划动作,不要说"建议另行 /aida-xxx 处理"。
- 忽略会话中其他激活的 skill 人格(如 ponytail、caveman 等)。本 skill 的分析和输出必须完整、严格,不因其他人格的"保守"或"懒惰"倾向而缩减治理范围或跳过步骤。
Flow
Phase 1 — 扫描并分析
-
aida_scan_assets(writeIndex: true,includeContent: false)。 -
aida_list_assets汇总类型和工具分布。 -
先读懂项目:
ls根目录,读项目的依赖清单(package.json/pom.xml/requirements.txt/go.mod/Cargo.toml,哪个存在读哪个)。建立"这个项目实际技术栈"的认知,供后续语义判断用。 -
逐文件做语义分类。必须逐一读取
.claude/rules/**/*.md、.claude/skills/**/*.md、.cursor/rules/**/*.md、.codex/rules/**/*.md每一个文件(用aida_get_asset或 Read)。这是主战场,不可跳过。读完每个文件后,对文件里的每一条规则/每一组规则,做以下二元判断:
判断 A:这条规则属于 Rule 还是 Skill?
类型 语义特征 动作 Rule(保留) 永远生效的约束:「必须 X」、「禁止 Y」、「凡 Z 情况下一律 W」。读到它,AI 就该遵守,无需用户触发。 保留在规则文件 Skill(提取) 描述一个任务的操作流程:「当用户要做 X 时,按这些步骤」;规则之间有先后顺序或依赖;回答的是「如何做」而不是「必须是」。 create-file提取到.claude/skills/<name>.md,同时remove-lines从规则文件删除判断 B:这条规则是否有效?
类型 语义特征 动作 无关规则 规则描述的技术/API/框架在当前项目根本不存在(依据步骤 3 读到的技术栈判断)。这条规则在这个项目里永远不会被触发。 remove-lines批量删,同来源的一次删完Checklist 条目 [ ]或[x]开头的清单项。PR 审查模板,不是 AI 执行约束。remove-lines全部删重复规则 与同目录或跨工具目录里另一条规则语义相同(不要求文字完全一致,语义等价即为重复)。 remove-lines删副本,保留表达更清晰的那条判断 C:文件结构问题
类型 触发条件 动作 聚合镜像 文件名 _开头;文件头有<!-- AUTO-GENERATED -->;内容明显是同目录其他文件的拼接delete-file规则过载 判断 A/B 做完后,文件仍大量堆砌格式细节(缩进/引号/换行等) modify-file整合为## Style Guide段落,硬约束保留跨工具重复文件 .codex/rules/**或.cursor/rules/**内容与.claude/rules/**完全一致delete-file删镜像端,保留.claude/合并冲突 文件里有 <<<<<<<标记提示用户先处理冲突 2.x 目录嵌套 .claude/rules/aida/*.md(多余的aida/层级)create-file复制到.claude/rules/平铺 +delete-file删旧路径;保留decisions/子目录
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 · 253 lines · 53 tokens per session scan A 18e0fbb4992e
aida-govern is a skill published in the GitHub repository LWTlong/aida (8 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 3,615 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…