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 weiyi88/cc-code --skill agent-featuregit clone --depth 1 https://github.com/weiyi88/cc-codeWrote 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/weiyi88/cc-code/agent-feature)<a href="https://agentmods.dev/skills/weiyi88/cc-code/agent-feature"><img src="https://agentmods.dev/badge/skills/weiyi88/cc-code/agent-feature/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/weiyi88/cc-code/agent-feature"><img src="https://agentmods.dev/badge/skills/weiyi88/cc-code/agent-feature.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00018 | $0.02280 |
| Opus 5.5 | $0.00007 | $0.00912 |
| Sonnet 5.5 | $0.00004 | $0.00456 |
| Haiku 4.5 | $0.00002 | $0.00228 |
Grade A, and why
agent-feature 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 today.
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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-feature — 双 agent × cc-code 驱动功能增量执行编排器
纯执行器:只执行增量需求,不规划。需求与契约由
/cc-code:plan-feature商讨定稿落盘,本命令读定稿文档直接开发,中途零确认,只在 FAIL 3 轮升级时交人。 增量铁律:只做「规划了但还没验过」的断言,绝不重推存量需求、绝不重做已 PASS 项。 与 agent-mvp 的分工:mvp 是「盖整栋楼」(含 agent-whole-qa 全量清算收口);feature 是「在楼里加一个房间」(affected 精准回归,无全量清算)。
前置检查(启动时一次性)
- 确认项目根存在
.cc_code/(否则提示先/cc-code:init)。 - 确认双 agent 可用:
dev/qa。 - 增量定位(⭐第一动作,见下节)——定位失败即拒跑,后续检查全免。
- 确认测试基建:读
project.md§六「测试基建契约」。缺失则把「补齐测试基建」作为 Dev 段首个任务。 同理读project.md§七「日志契约」:缺失或未填实(老项目常见)→ 把「搭日志基建 + 回填 §七」并入 Dev 段首个任务。 - 索引体检(静默):
codegraph status --json——pendingChanges非 0 → 静默codegraph sync(增量回归面建立在索引之上,旧索引 = 漏回归);initialized:false→ 报一行(⛔ 不自动重建)。CLI 未装则静默跳过(精准回归降级为全量)。⛔ 健康时一个字都不提。 - 执行
/cc-code:cc-code完成会话开启协议,锁定当前阶段与角色。
⭐ 增量定位(第一动作,纯查表,零推理)
① 读 status.md「下一步」
└─ 期望形态:「F-n <需求名>,已规划未开发」+ 点名断言号(如 A28.1~A28.10 / U23)
├─ 没有 F-n / 写的是「未规划」/ 下一步是别的事
│ → ⛔ 拒跑:「增量未规划,请先走 /cc-code:plan-feature」
│ (本命令绝不现场推需求——需求唯一来源 = 定稿文档)
└─ 拿到 F 号 + 新断言清单
② 读 prd.md §1.5 主表 / ux.md §2.3 矩阵 → 取这些断言号的具体内容
③ 读 gates.md 追溯矩阵 → 取已 PASS 断言集合
④ 对账:
增量范围 = F-n 点名断言 − gates.md 已 PASS
├─ 差集为空 → 报「F-n 已全部 PASS,无事可做」,结束
└─ 差集非空 → 即本次执行范围,进 Dev 段
断言编号永久稳定(A 序列不重排不复用),所以这个对账天然精确——已 PASS 的不会重做,没 PASS 的就是本次的活。
生命周期总览
启动 → 增量定位 → ①Dev → 校准 → ②QA → 校准
│
┌─────────┴──────────┐
▼ ▼
FAIL→回Dev(≤3) PASS→结算→结束
│ (⛔ 无全量清算)
3轮仍FAIL→升级(交人)
阶段执行规范
① Dev 段(agent: dev)
| 项 | 内容 |
|---|---|
| 读 | status, prd(仅 F-n 命中模块小节 + §1.5 命中断言), ux(命中 U 项), project(含实现指引章节), data / api(仅命中契约小节) |
| 做 | 只按增量范围实现:改写命中模块 + 新增/补齐测试;遵循 project.md 约定;⛔ 不重构无关代码 |
| 跑 | Agent(dev) → 自检:pnpm lint → tsc --noEmit → pnpm test → pnpm test:e2e |
| 输出 | 增量代码 + 测试 + 完成报告(文件清单 + pass/fail) |
| 写 | src/, project.md §六 声明的测试根 |
| ⭐ 完成后 | 算精准回归面:codegraph affected <本段改动的源文件...> → 测试文件清单传给 ②QA 段;非 .spec/.test 命名补跑 --filter "<project.md §六 登记的 glob>",合并去重即「本段回归范围」 |
| ✅ 完成后 | 执行 /cc-code:cc-code 校准(静默) |
What ships with it
1 file 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.
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.
- today Changed · +1 lines 508c3c6e14da
- 1mo ago Changed · -127 tokens per session a56f01c53252
- 1mo ago First seen · 105 lines · 145 tokens per session scan A d702c7faf6ec
agent-feature is a skill published in the GitHub repository weiyi88/cc-code (5 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 2,280 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-13.
Other skills, from other repositories
Jira QA Workflows
Run QA work in Jira like a professional, bug lifecycle and triage, JQL queries for testers, quality dashboards, sprint QA rituals, and REST API automation for bulk bug operations and reporting.
ai-team-orchestration
Bootstrap and run a multi-agent AI development team. Use when: starting a new software project with AI agents, setting up parallel dev/QA teams, creating sprint plans, writing brainstorm prompts with distinct agent voices, recovering a project workflow, or planning sprints.
state-machine
Task lifecycle state transitions with validation gates. Defines states, triggers, and required proofs.
subtask-update
Update subtask with fixes or new steps. Two trigger modes: (A) Auto-called by autoworker:gate-check on FAIL — reads FAIL info, adds supplementary steps. (B) User calls with a finding/bug during testing — diagnoses, fixes, updates subtask. Both modes end by invoking autoworker:dispatch to re-enter the loop.
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.