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 agentmods add skills/weiyi88/cc-code/experience-summarynpx skills add weiyi88/cc-code --skill experience-summarygit clone --depth 1 https://github.com/weiyi88/cc-codeWhat 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 | $0.00115 | $0.00922 |
| Opus 5 | $0.00057 | $0.00461 |
| Sonnet 5 | $0.00023 | $0.00184 |
| Haiku 4.5 | $0.00012 | $0.00092 |
Grade A, and why
experience-summary 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 2d 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
/cc-code:experience-summary — 项目级开发经验沉淀器
把「这次踩的坑」变成「下次的准出门槛」。 落点是项目级
.cc_code/references/（跟随项目走，不进插件、不进全局）。
⛔ 五条铁律
- 项目级唯一落点：只写当前项目
.cc_code/references/，⛔ 禁写插件目录、全局~/.claude/。 - 命名规范：
[角色]-[具体事件域]-references.md- 角色小写：
architect/dev/qa/pm - 事件域 = 技术或流程主题，kebab-case，不含日期
- ✅
architect-bull-redis-queue-references.md - ❌
arch-xp.md（无事件域）❌20260807-bug-references.md（含日期）
- 角色小写：
- 内容精炼：只写「设计/验收时应该怎么思考、怎么做」，⛔ 禁写溯源叙事、清理修复过程、流水账。
- 按需读取：必须登记
.cc_code/references/INDEX.md（按角色分组，一行式「何时读」），⛔ 禁要求角色每次全读。 - 不越权：⛔ 禁改
active/任何状态文件（Agent.md 权限表、status.md 等）——references 是补充资料，不是状态机。唯一例外：主人当场明确要求把 INDEX 挂进Agent.md某角色[按需读]，可代笔加一行。
执行流程
① 定位角色 本次经验归谁：architect / dev / qa / pm
② 提炼准则 从对话/踩坑中抽出「必答问题 + 设计准则」
每条准则 = 一句话规则 + 一句话为什么
③ 主人过目 先输出草稿给主人看，确认后才落盘（禁先斩后奏）
④ 落盘 写 .cc_code/references/[角色]-[事件域]-references.md
⑤ 登记索引 更新 .cc_code/references/INDEX.md（无则新建）：
| 文件 | 何时读 |
⑥ 挂载请示 若该角色 Agent.md 未挂 INDEX，请示主人是否加 [按需读] 行
文件模板
# [角色] 事件域经验标题
> 何时读：一句话触发条件（如「设计异步队列/中间件时必读」）。
> 由 /cc-code:experience-summary 沉淀，索引见 INDEX.md。
## 必答 N 问（准出门槛）
1. 故障场景 A → 谁兜底？
2. 故障场景 B → 谁消费？
（答不出 → 方案不准进下一角色）
## 设计准则
- **加粗规则**：一句话解释为什么。
- ……
质量标准
- 全文 ≤ 30 行；读一遍 ≤ 2 分钟。
- 准则必须可执行（能据此否决一个方案），禁空泛口号（如「注意性能」）。
- 同一事件域已有文件 → 更新该文件，不开新文件。
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.
- 2d ago First seen · 63 lines · 115 tokens per session scan A 791593b49a6e
experience-summary is a skill published in the GitHub repository weiyi88/cc-code (5 stars, last pushed 7d ago), licensed MIT. It adds 115 tokens to every session and 922 once invoked, about $0.0006 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
state-machine
Task lifecycle state transitions with validation gates. Defines states, triggers, and required proofs.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
mutation-testing
Mutation testing patterns for verifying test effectiveness. Use when analyzing branch code to find weak or missing tests.
planning
Planning work in small, known-good increments. Use when starting significant work or breaking down complex tasks.
testing
Testing patterns for behavior-driven tests. Use when writing tests or test factories.
davinci-define
Apply the 7 Da Vincian Principles to define problems, set direction, and reflect on life choices. Use for career decisions, goal setting, life planning, or when you need to clarify what the real question is before solving it.