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 ArchSightLabs/archsight-cognition --skill retrogit clone --depth 1 https://github.com/ArchSightLabs/archsight-cognitionWrote 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/archsightlabs/archsight-cognition/retro)<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>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 | $0.00049 | $0.01094 |
| Opus 5 | $0.00024 | $0.00547 |
| Sonnet 5 | $0.00010 | $0.00219 |
| Haiku 4.5 | $0.00005 | $0.00109 |
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.
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
- 先写事实和影响,不急于归因。
- 区分技术、流程、激励、沟通、能力和外部约束。
- 找出可阻断的根因,而不是只描述表面现象。
- 把改进动作写成责任人、期限、指标和复盘时间。
- 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。
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.
- 7d ago First seen · 106 lines · 49 tokens per session scan A 8a8987dcf27c
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.
Other skills, from other repositories
gws-tasks
Google Tasks: Manage task lists and tasks.
gws-workflow-email-to-task
Google Workflow: Convert a Gmail message into a Google Tasks entry.
gws-workflow-standup-report
Google Workflow: Today's meetings + open tasks as a standup summary.
persona-project-manager
Coordinate projects — track tasks, schedule meetings, and share docs.
persona-customer-support
Manage customer support — track tickets, respond, escalate issues.
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.