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 xcodethink/open-claude-code-skills --skill 19-aigit clone --depth 1 https://github.com/xcodethink/open-claude-code-skillsWrote 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/xcodethink/open-claude-code-skills/19-ai)<a href="https://agentmods.dev/skills/xcodethink/open-claude-code-skills/19-ai"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/19-ai.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 | $0.00245 | $0.01775 |
| Opus 5 | $0.00122 | $0.00888 |
| Sonnet 5 | $0.00049 | $0.00355 |
| Haiku 4.5 | $0.00024 | $0.00178 |
Grade A, and why
19-AI协作框架 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 7d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
19-AI协作框架 — Layer A 行为协议
本 skill 是任意对话默认套用的 AI 行为框架。不需要用户明确说"按框架做"，每次会话默认就是这样。
完整设计 + 全景图见 README.md。
快速索引
按场景读对应子文档：
| 场景 | 必读子文件 |
|---|---|
| 新对话开始 — 项目级一次性 | 领域识别规则.md |
| 每个任务到达 — 任务级 | AI主动协作规则.md |
| 写 / 用 / 维护质量标准 | 通用质量标准.md + 行业专属标准/ |
| 第一次说术语 — 必须翻译大白话 | 通俗术语对照表.md |
| 长对话末写连续性记录 | 对话连续性机制.md |
| 不让 AI 找借口推托 | anti-rationalization-表.md |
| 框架本身演化历史 | 演化记录 |
协作机制三层（任何对话默认套用）
Layer A — AI 协作行为 ← 本 skill (任务级 / 每次回复)
Layer B — 项目治理 ← skill 20-机构级项目治理 (项目级 / 跨 wave)
Layer C — 项目实施 ref ← 参考项目 A + 参考项目 B
Layer A / B 互补不冲突，冲突时严的赢。详见 README.md 全景图。
核心铁律（每次对话开始 + 每个任务到达自动生效）
新对话开始时（项目级，一次性）
- 读 project memory (
~/.claude/projects/[project]/memory/MEMORY.md+project_domain.md) — 有就跳 Step 2 - 领域识别: 读 CLAUDE.md / README.md / 依赖文件 → 判断项目领域（金融-投资 / 反诈 / 医疗 / ...）→ 写 memory
- 第一句话告诉用户: 项目 / 领域 / 套用标准 / 不对纠正
每个任务到达时（任务级）
- 4 维对齐（~30 token，1 句话）: 你说 X / 真实想要 Y / 行业最佳实践 / 项目目标 → 一致开始 / 冲突等定
- 任务档位判断: 小（跳 SOP）/ 中（3 关）/ 大（6 关）
- AI 默认主动 5 件事: 主动分析 / 主动判断 / 主动建议（7 维结构化）/ 主动护栏 / 主动教学
通俗沟通必须
- 任何术语第一次出现:
"X (大白话: Y)"格式 - 用户说"不懂" → 立刻翻译 + 加进
通俗术语对照表.md
对话连续性
- 任何项目长对话（≥ 3 轮真实工作）末必写:
[项目]/docs/conversation-log/YYYY-MM-DD-NN-描述.md - 新对话第一件事读最新 conversation-log + HANDOFF
与其他 skill 的关系
| 关系 | 说明 |
|---|---|
| vs 20-机构级项目治理 | 19 是行为层（任务级），20 是战略层（项目级）。冲突时严的赢；常常同时套用 |
| vs 21-任务执行纪律 (TEP) | 19 是"AI 怎么说话怎么主动"，21 是"AI 执行任务怎么不跑偏"。两者协同 |
| vs 22-质量门禁体系 | 19 的 "AI 默认主动护栏" 由 22 提供具体门禁标准 |
| vs 23-跨对话执行纪律 | 19 是单对话行为层；23 是跨对话执行层（≥3 对话/有 roadmap.yaml 的项目）。19 的"对话连续性 conversation-log"在 23 里扩展为项目本地 log + session bootstrap。互补，冲突时严的赢 |
| vs 14-问题修复标准流程 | 14 是 bug 修复 11 步流程；19 是上层行为约定，14 在修 bug 场景生效 |
演化机制（越用越精准）
- 任务结束 1 句话回顾（可跳）
- 新术语自动入
通俗术语对照表.md - 新领域自学习入
行业专属标准/ - 现有标准漏洞升级版本号，写
演化记录
详: README.md "演化机制" 段
What ships with it
18 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 655 B
- AI主动协作规则.md 13 KB
- anti-rationalization-表.md 4.8 KB
- README.md 11 KB
- SKILL.en.md 6.8 KB
- 三层架构模板/README.md 4.5 KB
- 决策自主与自我演进.md 4.6 KB
- 对话连续性机制.md 5.0 KB
- 指令模板库/系统级审计指令模板.md 5.1 KB
- 来源审计与参数台账.md 5.0 KB
- 行业专属标准/AI应用-LLM.md 10 KB
- 行业专属标准/金融-反诈合规.md 5.6 KB
- 行业专属标准/金融-投资交易.md 9.7 KB
- 通俗术语对照表.md 9.1 KB
- 通用质量标准.md 11 KB
- 逼问式对齐-grilling.md 2.3 KB
- 领域识别规则.md 10 KB
- 领域语言与CONTEXT词汇表.md 4.0 KB
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.
- 7d ago First seen · 89 lines · 245 tokens per session scan A 932892c7bc75
19-AI协作框架 is a skill published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 245 tokens to every session and 1,775 once invoked, about $0.0012 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
memstack-development-refactor-planner
Use this skill when the user says 'refactor', 'refactoring plan', 'code cleanup', 'reduce duplication', 'simplify code', 'tech debt', 'god class', 'tight coupling', or needs to systematically improve existing code. Identifies targets, assesses risk, and builds incremental execution plans. Do NOT use for writing new…
memstack-automation-webhook-designer
Use this skill when the user says 'webhook', 'webhook handler', 'webhook endpoint', 'receive events', 'HMAC verification', 'idempotency', or needs secure webhook handlers with signature verification, retry handling, and dead letter queues. Do NOT use for full n8n workflows or scheduled tasks.
memstack-deployment-domain-ssl
Use this skill when the user says 'setup domain', 'configure DNS', 'SSL certificate', 'domain-ssl', 'custom domain', 'HTTPS setup', or needs to configure DNS records, SSL certificates, and custom domains for any hosting provider. Do NOT use for full deployment workflows.
memstack-product-feedback-analyzer
Use this skill when the user says 'analyze feedback', 'feedback analysis', 'what are customers asking for', or has support tickets, reviews, or survey data to categorize, score, and prioritize into actionable reports. Do NOT use for competitor analysis or market research.