Borrowing it
Nothing to install: this file belongs to MT-gar/Nexus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MT-gar/Nexus/main/.claude/skills/devflow/agents/rca/SKILL.mdgit clone --depth 1 https://github.com/MT-gar/NexusWrote 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/mt-gar/nexus/rca)<a href="https://agentmods.dev/skills/mt-gar/nexus/rca"><img src="https://agentmods.dev/badge/skills/mt-gar/nexus/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/mt-gar/nexus/rca"><img src="https://agentmods.dev/badge/skills/mt-gar/nexus/rca.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 | $0.00045 | $0.00872 |
| Opus 5.5 | $0.00018 | $0.00349 |
| Sonnet 5.5 | $0.00009 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
root-cause-analysis 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 1mo 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
Skill：root-cause-analysis（代码根因定位）
1. 业务用途
对聚合后的规范缺陷进行代码级根因定位：结合日志/错误信息定位可疑代码路径，确认根因机制与影响面（波及模块、调用方、用户），产出结构化 RCA 报告。通过检索研发知识库复用既往根因结论（轻量 RAG），避免重复排查。对应 8 步闭环的"工具调用"环节。
2. 输入输出 Schema
输入：
{ defect_id: string, defect_title: string, defect_description: string,
severity: string, 可选的日志/堆栈: string }
输出（RCA 报告消息）：
{ 根因: { 代码位置: string, 机制解释: string, 证据: string },
影响面: { 模块: string[], 调用方: string[], 用户影响: string },
修复建议: string,
参考知识: Array<{ knowledge_id, title, 相似度 }> }
3. 调用触发条件
- manager 创建"根因定位"任务（RCA 报告作为修复任务的输入规格）
- 修复失败回退时重新定位（补充信息后重试）
4. 依赖工具
| 工具 | 用途 |
|---|---|
list_defects |
读取缺陷详情 |
search_knowledge |
知识库检索（root-cause/fix-pattern 标签命中既往案例） |
update_defect |
回写 rca_task_id、状态置 fixing |
claim_task / update_task / wait_for_work |
任务生命周期 |
| 客户端原生能力 | 代码库搜索/阅读、日志查询（grep、git log/blame） |
5. 失败重试 / 降级机制
- 信息不足（缺复现/日志）→ 任务置
blocked，报告 manager 补充信息，不瞎猜根因 - 知识库命中既往根因 → 直接复用并标注引用，仍验证当前代码位置是否一致
- 降级：无法访问代码库时输出"基于日志证据的根因假设 + 待验证清单"，由 fixer 验证
6. 安全权限边界
- ✅ 允许：只读操作（list_defects / search_knowledge / 代码阅读）
- ❌ 禁止：修改代码、执行发布、审批操作、
update_defect中修改 severity 之外的业务字段（仅允许回写 rca_task_id 与状态） - ⚠️ RCA 报告中的敏感信息（密钥/用户数据）脱敏后再发消息
7. 多场景复用价值
- 代码缺陷根因定位（本场景）
- 告警根因定位（监控指标异常 → 关联服务与代码 — 零人工运维方向）
- 故障排查助手（任何"现象 → 根因"的分析场景，配合知识库复用）
8. 与多 Agent 协作链路
triage-agent ──缺陷看板──▶ devflow-manager ──RCA 任务──▶ rca-agent
rca-agent ──RCA 报告──▶ devflow-manager ──修复任务(附 RCA)──▶ fixer-agent
RCA 报告是修复任务的输入规格；通过 search_knowledge 与 retro-agent 沉淀的知识库形成"经验复用"回路。
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.
- 1mo ago First seen · 68 lines · 45 tokens per session scan A e090b5cb2dc1
root-cause-analysis is a skill published in the GitHub repository MT-gar/Nexus (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 872 once invoked, about $0.0002 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 2026-09-20.
Other skills, from other repositories
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.
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…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…