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 protect-my-hair/nucleus-marketplace --skill defect-intake-rcagit clone --depth 1 https://github.com/protect-my-hair/nucleus-marketplaceWrote 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/protect-my-hair/nucleus-marketplace/defect-intake-rca)<a href="https://agentmods.dev/skills/protect-my-hair/nucleus-marketplace/defect-intake-rca"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/defect-intake-rca/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/protect-my-hair/nucleus-marketplace/defect-intake-rca"><img src="https://agentmods.dev/badge/skills/protect-my-hair/nucleus-marketplace/defect-intake-rca.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01227 |
| Opus 5 | $0.00019 | $0.00613 |
| Sonnet 5 | $0.00008 | $0.00245 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade A, and why
defect-intake-rca 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 12d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Defect Intake RCA
前置:使用本 Skill 前,先按
using-nucleus完成 Nucleus 入口识别(Claude Code 会话由插件 SessionStart hook 自动注入该纪律)。
用于 Nucleus V2 缺陷受理 workflow 基线:在 Claude Code / Codex 内做缺陷受理质量评估和 RCA 候选证据生成。这是 coding-agent 插件运行时,不是 PMS 后端 workflow。
核心原则
缺陷受理和 RCA 只能生成可审查的质量评估与根因候选证据;它不能确认根因、修复代码、验证回归、关闭缺陷、创建 PR/MR 或推进 PMS 状态。
缺少 defectId、stage、结构化复现、log / failing test / failed test report、primary feature 或 feature doc 时,不得生成 RCA candidate,必须先补齐缺陷上下文。
RCA candidate、review checklist、summary 或 result 不能替代人工 RCA review、根因确认、修复完成、测试通过或缺陷关闭事实。
到达 rca-review 人审点时,按 _shared/references/subagent-precheck-protocol.md 执行 subagentPreReview 子代理预审;未取得“材料可提交人工审查”结论前,不得请求人工 RCA review。
Checklist
启动本 Skill 后,必须先为以下每一项创建宿主 todo/task,并按顺序执行;Codex 使用计划 / 任务工具,Claude Code 使用 TodoWrite 或等价宿主 todo。每完成、阻塞、等待人工补齐或等待 review 一项,都必须逐项更新状态;若等待项触达人审点,先完成 subagentPreReview 并确认材料可提交人工审查。
- 读取缺陷上下文:读取
.nucleus/context/<workflowRunId>.json、defect context artifacts 和 primary feature doc;缺关键输入时ALERT_AND_BLOCK。 - 创建宿主任务包:把本 checklist 同步成当前会话的宿主 todo/task;未同步前不得生成 intake quality 或 RCA candidate。
- 校验受理质量:检查 defectId、stage、复现、日志或失败测试、session binding 和写入边界。
- 补齐缺陷信息:缺少关键上下文时,只呈现缺口并提出当前最关键补齐问题,按
references/defect-info-request-format.md组织提问;没有明确补齐事实时 STOP。 - 生成 intake quality 证据:只写
.nucleus/runs/<workflowRunId>/defects/intake-quality.*,不得写源码、测试、PR/MR 或缺陷状态。 - 生成 RCA candidate:基于已验证上下文生成根因候选和 review checklist;candidate 仍是待审证据。
- 等待 RCA review:向用户或 PMS 呈现候选、非事实和待确认项;缺人工 review 时 STOP。
- 写入结果证据:构建 result package;
NEEDS_HUMAN_REVIEW不代表根因确认、修复完成、测试通过或缺陷可关闭。
Runtime
python3 skills/defect-intake-rca/scripts/defect_intake_rca.py analyze \
--repo-root <target-repo> \
--context <target-repo>/.nucleus/context/<workflowRunId>.json
仅校验器使用的可选参数:
--candidate-output <target-repo>/.nucleus/runs/<workflowRunId>/defects/rca-candidate.json
必需输入
What ships with it
12 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 645 B
- assets/defect-rca-candidate-template.json 1.4 KB
- assets/defect-rca-candidate-template.md 747 B
- assets/intake-quality-template.json 294 B
- assets/intake-quality-template.md 160 B
- assets/nucleus-defect-rca-candidate.schema.json 8.8 KB
- references/blocker-matrix.md 1014 B
- references/candidate-schema.md 565 B
- references/defect-boundary.md 635 B
- references/defect-info-request-format.md 1.3 KB
- references/session-binding-boundary.md 485 B
- scripts/defect_intake_rca.py 39 KB runs code
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.
- 12d ago First seen · 77 lines · 39 tokens per session scan A ccf298dbeb17
defect-intake-rca is a skill published in the GitHub repository protect-my-hair/nucleus-marketplace (162 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,227 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.