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/retro/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/retro)<a href="https://agentmods.dev/skills/mt-gar/nexus/retro"><img src="https://agentmods.dev/badge/skills/mt-gar/nexus/retro/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/retro"><img src="https://agentmods.dev/badge/skills/mt-gar/nexus/retro.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 | $0.00050 | $0.00943 |
| Opus 5.5 | $0.00020 | $0.00377 |
| Sonnet 5.5 | $0.00010 | $0.00189 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
retro-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：retro-analysis（研发复盘）
1. 业务用途
发布（或缺陷链路）结束后执行复盘：汇总发布/回滚/缺陷/审计轨迹数据，输出结构化复盘报告（根因总结、影响面、改进措施），并将可复用结论沉淀为知识条目（root-cause 根因模式 / fix-pattern 修复模式 / rule 规则 / lesson 教训），供后续 RCA 通过 search_knowledge 复用。对应 8 步闭环的"经验沉淀"环节，也是 4 选 2 强制落地中的"Agent 记忆/知识库"能力。
2. 输入输出 Schema
输入：
{ 复盘任务: { task_id, description: 发布 ID / 缺陷 ID 列表 } }
输出：
{ 复盘报告: { retro_id, title, root_cause, impact, action_items },
知识条目: Array<{ knowledge_id, title, tags, source: "retro" }> }
3. 调用触发条件
- manager 创建"复盘任务"（依赖发布任务完成）
- 回滚发生后（发布 failed/rolled_back）优先复盘，沉淀教训
4. 依赖工具
| 工具 | 用途 |
|---|---|
list_releases |
发布记录（含回滚 metadata） |
list_defects |
缺陷链路（聚合/RCA/修复记录） |
query_audit_logs |
全链路执行轨迹（谁在何时做了什么） |
create_retro |
创建复盘报告（根因/影响/改进措施） |
publish_knowledge |
沉淀知识条目（自动回写 retro.knowledge_ids） |
search_knowledge |
去重检查：结论已沉淀则不重复（标注引用） |
5. 失败重试 / 降级机制
- 结论已在知识库（search_knowledge 命中）→ 不重复沉淀，标注"已存在"并补充引用
- 无发布记录（缺陷未走到发布）→ 聚焦缺陷链路复盘，产出防御性措施
- 降级：数据不全时复盘报告标注"基于现有证据"，知识沉淀仍强制（至少沉淀 1 条 lesson）
6. 安全权限边界
- ✅ 允许：
create_retro/publish_knowledge/search_knowledge/ 只读查询 - ❌ 禁止：修改缺陷/发布/审批状态、审批操作、写代码
- ⚠️ 复盘内容含事故细节，消息中脱敏（用户数据/密钥）；知识条目只存可复用结论，不存敏感样本
7. 多场景复用价值
- 研发复盘（本场景）
- 事故复盘（任何线上事故 — 零人工运维方向）
- 知识库建设（团队经验沉淀，供 RAG 检索）
- 持续改进（改进措施 → 规则沉淀 → 告警规则/检查清单升级）
8. 与多 Agent 协作链路
release-agent ──live/failed──▶ devflow-manager ──复盘任务──▶ retro-agent
retro-agent ──复盘报告+知识──▶ devflow-manager ──汇报──▶ 用户
retro-agent ──publish_knowledge──▶ 知识库 ──search_knowledge──▶ rca-agent（经验复用回路）
复盘是闭环的收尾：把一次缺陷处置的经验沉淀为后续处置的输入，形成组织级学习。
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 · 50 tokens per session scan A 585c1531664d
retro-analysis is a skill published in the GitHub repository MT-gar/Nexus (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 943 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
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.
inspector-workbench
Runs Inspector UI work on the standalone Threads state lab so the agent can see the overlay. Use when a CopilotKit employee asks an agent to fix, polish, add, or debug Inspector UI, chrome, panes, overlay actions, launcher, Home, Threads, Playground, Memory, or any visual behavior in @copilotkit/web-inspector. Don't…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
browserwing-admin
Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.
code-understand
Map the load-bearing files, symbols, callers, and dependencies of an unfamiliar codebase before making changes. Use for architecture orientation, impact analysis, what-would-break questions, or finding callers. Uses CodeGraph when available and a dependency-free builtin fallback.