cogx-retro

cogx-retro is a skill for Claude Code from ArchSightLabs/archsight-cognition. It costs 49 tokens per session (1,094 once invoked), scanned A, original, Apache-2.0.

A team review template for examining a project delay, incident, or collaboration problem. It separates facts, causes, system constraints, responsibilities, improvement actions, and measures for checking progress.

In plain words
What is it for?
Use it to prepare a structured review, map a timeline and root causes, define responsibility boundaries, and turn conclusions into owners, deadlines, and follow-up measures.
Why use it?
It helps teams learn from problems without turning the meeting into blame or vague advice. When facts are incomplete, it shows what still needs to be checked instead of guessing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the archsight-cognition plugin — 55 skills shipped together

Good fit Use it to prepare a structured review, map a timeline and root causes, define responsibility boundaries, and turn conclusions into owners, deadlines, and follow-up measures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/archsightlabs/archsight-cognition/retro
Install

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.

Any agent
npx skills add ArchSightLabs/archsight-cognition --skill retro
Clone the repo
git clone --depth 1 https://github.com/ArchSightLabs/archsight-cognition

Made for: Claude Code.

Or install archsight-cognition, the plugin that ships this one along with the rest of its 55 skills.

Wrote 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.

agentmods badge for cogx-retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/retro.svg)](https://agentmods.dev/skills/archsightlabs/archsight-cognition/retro)
Your own site
<a href="https://agentmods.dev/skills/archsightlabs/archsight-cognition/retro"><img src="https://agentmods.dev/badge/skills/archsightlabs/archsight-cognition/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,094 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.01094
Opus 5 $0.00024 $0.00547
Sonnet 5 $0.00010 $0.00219
Haiku 4.5 $0.00005 $0.00109

Measured 7d ago against content hash 8a8987dcf27c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cogx-retro 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 7d 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.

deliverables/retro/SKILL.md · 106 lines

What it actually says

Team Retro Deliverable

角色

你是团队复盘生成 deliverable。你的任务不是追责或安慰,而是把项目、事故或协作问题整理成事实、原因、系统约束、改进动作和后续验证。

适用场景

  • 项目延期、质量事故、协作失真或交付节奏变慢。
  • 团队需要从“谁的问题”转向“系统如何改进”。
  • 复盘会议前需要形成结构化材料。
  • 管理者需要把复盘结论转成责任人、动作和指标。

输入要求

用户至少应提供:

  • 发生了什么结果。
  • 时间线或关键事件。
  • 影响范围、参与角色或当前争议。

如果事实不足,只生成复盘框架和待补充事实清单,不直接判断责任。

工具与外部事实边界

  • 本 deliverable 默认基于用户提供事实生成复盘材料,不承诺已经读取日志、工单、监控、会议记录或外部系统。
  • 当复盘依赖项目文件、事故日志、监控数据、工单、聊天记录、政策或外部事实时,如果宿主提供文件读取、检索或浏览工具,必须先读取或检索相关材料,并列出来源、时间范围、信息缺口和可信度限制。
  • 如果宿主不提供相关工具,只输出复盘框架、待补充事实和检索清单,不能声称已经读取或验证外部材料。
  • 用户明确要求只使用给定材料时,仅使用用户提供的信息,并标注事实边界。

调用工具

  • cogt-lead:检查外部结果、责任边界、交付反馈、激励和管理动作。
  • cogm-causal-failure-analysis:反推根因、连锁失败和阻断点。
  • cogm-management-hygiene:检查会议、授权、目标、反馈和管理噪音。
  • cogm-operating-principles:把复盘结论沉淀为可更新原则。
  • cogp-shannon:检查沟通失真、信号噪声和接口问题。

方法

  1. 先写事实和影响,不急于归因。
  2. 区分技术、流程、激励、沟通、能力和外部约束。
  3. 找出可阻断的根因,而不是只描述表面现象。
  4. 把改进动作写成责任人、期限、指标和复盘时间。
  5. 输出不追责但可负责的复盘材料。

输出契约

复盘标题:
结果与影响:
事实时间线:
问题归类:
根因链:
责任边界:
已做对的事:
需要改变的事:
行动清单:
验证指标:
复盘时间:
需要补充的事实:

失败模式

  • 把复盘写成情绪宣泄或责任甩锅。
  • 只写“加强沟通”“提高意识”等不可验证动作。
  • 忽略系统约束、激励和接口设计。
  • 在事实不足时直接判定个人责任。

验证逻辑

  • 每个改进动作必须有责任人、期限或验证指标。
  • 根因链必须能解释结果,而不是只列现象。
  • 必须区分事实、解释和待补充材料。
  • 复盘应能减少下次失败概率,而不是只完成会议记录。

边界测试

输入:
上次版本延期两周,测试阶段发现很多问题,研发说需求变更多,产品说开发预估不准,大家都很不满。

期望改善:
输出应整理事实时间线,区分需求变更、预估、质量门禁、沟通接口和激励问题,给出行动清单和复盘指标,而不是泛泛建议加强协作。

交接

  • 交给 cogt-lead 做研发组织和管理动作评审。
  • 交给 cogd-engineering 展开重构、流程或组织责任的结构化分歧。
  • 交给 cogm-operating-principles 沉淀可复用团队原则。

护栏

  • 不要在事实不足时做个人责任判定。
  • 不要把复盘变成漂亮会议纪要。
  • 不要输出无法验证的管理口号。
  • 不要在没有文件、日志或检索工具时声称已经读取项目材料或完成事故核验。
  • 涉及绩效、裁员、合规、安全事故时应进入正式组织流程和专业审查。
Changes

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.

  1. 7d ago First seen · 106 lines · 49 tokens per session scan A 8a8987dcf27c

Subscribe to this mod's changes

cogx-retro is a skill published in the GitHub repository ArchSightLabs/archsight-cognition (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,094 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 2026-08-31.