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-debuggit 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-debug)<a href="https://agentmods.dev/skills/weiyi88/cc-code/agent-debug"><img src="https://agentmods.dev/badge/skills/weiyi88/cc-code/agent-debug/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-debug"><img src="https://agentmods.dev/badge/skills/weiyi88/cc-code/agent-debug.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 | $0.00019 | $0.02288 |
| Opus 5.5 | $0.00008 | $0.00915 |
| Sonnet 5.5 | $0.00004 | $0.00458 |
| Haiku 4.5 | $0.00002 | $0.00229 |
Grade A, and why
agent-debug 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-debug — 双 agent × cc-code 驱动 bug 修复执行编排器
纯执行器：只修已诊断的 bug，不诊断。根因与方案由
/cc-code:plan-debug落盘到active/bugs.md的 B-n 条目，本命令读 B-n 直接开发，中途零确认，只在 FAIL 3 轮升级时交人。 与 agent-feature 的分工：feature 是「加一个房间」（执行 F-n 需求增量）；本命令是「修房子里的漏水点」（执行 B-n bug 修复）。执行循环、回归策略、结算纪律全部同构。 初衷铁律：完整地修复 bug —— 修复面 = B-n 用例 + affected 影响面，⛔ 无 agent-whole-qa、无全量回归。
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。 - 索引体检（静默）：
codegraph status --json——pendingChanges非 0 → 静默codegraph sync；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：「B-n 待修复」+（bugs.md 里有对应 OPEN 条目）
├─ 没有 B-n / 写的是「未诊断」/ 下一步是别的事
│ → ⛔ 拒跑：「bug 未诊断，请先走 /cc-code:plan-debug」
│ （本命令绝不现场诊断根因——根因唯一来源 = B-n 条目）
└─ 拿到 B 号 + 条目内容（复现/期望出处/根因/方案/影响面）
② 读 gates.md → 查该 B-n 是否已有 PASS 记录
③ 对账：
已有 PASS → 报「B-n 已修复，无事可做」，结束
无 PASS → B-n 即本次执行范围，进 Dev 段
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, bugs.md（仅 B-n 条目）, prd / ux（仅期望出处命中的断言/判定项）, project（含实现指引章节）, data / api（仅命中契约小节） |
| 做 | 只按 B-n 方案修：根因处修复 + 按「影响面」清单逐文件核对连带；遵循 project.md 约定；⛔ 不重构无关代码、不改契约 |
| 探针 | B-n「需加探针」非「无」时：先按其加临时日志，每条带标记 CC-PROBE-B<n>，走 project.md §七 门面（DEBUG 级）→ 复现取证 → 修复 → ⛔ 交 QA 前删光（rg CC-PROBE-B<n> 零命中） |
| 跑 | Agent(dev) → 自检：pnpm lint → tsc --noEmit → pnpm test → pnpm test:e2e |
| 输出 | 修复代码 + 完成报告（文件清单 + pass/fail） |
| 写 | src/, project.md §六 声明的测试根 |
| ✅ 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 a4df60895db3
- 1mo ago Changed · -143 tokens per session 5e9ee6c5e556
- 1mo ago First seen · 101 lines · 162 tokens per session scan A 475d54f9f2fb
agent-debug is a skill published in the GitHub repository weiyi88/cc-code (5 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 2,288 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
debugging-workflow
Find the cause of a defect by hypothesis and bisection rather than by guessing, then fix it behind a regression test. Use when the user reports a bug, a crash, a test that fails intermittently, a performance regression or a production incident, asks why code behaves unexpectedly, or when the task involves reproducing…
engineering-playbook
A generic senior-engineer operating playbook. MANDATORY for every coding task — plan before you type, test before you claim, debug from evidence, review your own diff.
superpowers-systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
evoflow-debugging
A structured debugging guide for investigating EvoFlow bugs, mismatched behavior, incorrect data, and failed tests.
absolute-deflake
Flaky test fixes: detect nondeterministic tests empirically (repeat/shuffle/parallel runs), diagnose the root cause, fix it — never retry/skip/sleep — and verify across many randomized runs. Triggers on "absolute deflake", "fix flaky tests", "CI is flaky", "this test fails randomly/intermittently".
software-development-workflows
Use when planning, debugging, testing, reviewing, simplifying, or spiking code changes across languages: systematic debugging, TDD, debugpy/Node inspectors, code cleanup, and implementation strategy.