A structured weekly retrospective for a department. It reviews tasks and evidence from an ISO calendar week, then records findings and the next planning goal.

Use it to close a work week, review commitments, gather task facts, interview the relevant work areas, and save the results in dated HTML and project records.

It helps reconcile planned work with actual results and catches unfinished tasks or conflicts between local records and GitHub Issues.

retro — Skill for Claude Code by serejaris/personal-corp-os

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/serejaris/personal-corp-os

agentmods

npx agentmods add skills/serejaris/personal-corp-os/retro

Made for: Claude Code.

Or install personal-corp-os, the plugin that ships this one along with the rest of its 32 skills, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/serejaris/personal-corp-os/retro/github.svg)](https://agentmods.dev/skills/serejaris/personal-corp-os/retro)

Your own site

<a href="https://agentmods.dev/skills/serejaris/personal-corp-os/retro"><img src="https://agentmods.dev/badge/skills/serejaris/personal-corp-os/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/serejaris/personal-corp-os/retro"><img src="https://agentmods.dev/badge/skills/serejaris/personal-corp-os/retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 862 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium analysis-evasion · line 1
Suspicious Unicode normalization or mixed-script content

Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00075	$0.00862
Opus 5.5	$0.00030	$0.00345
Sonnet 5.5	$0.00015	$0.00172
Haiku 4.5	$0.00007	$0.00086

Measured 27d ago against content hash b228e66115e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 27d 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.

skills/retro/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retro

Запускается из штаба. Смотрит назад на неделю по задачам всех отделов.

Правило данных

Каждый запуск читает файлы задач заново. Своей копии задач не держи и неделю из памяти чата не восстанавливай. Файл ретро это срез со ссылками, источник правды остаётся в задачах отделов.

Шаги

Определи текущую ISO-неделю и её даты из системного времени. Если человек назвал другую неделю, возьми её.
Прочитай файл правил штаба (CLAUDE.md или AGENTS.md). Найди строки, где лежат задачи отделов, например: Обучение: ../corp-learn. Задачи отдела лежат в ../corp-learn/tasks/.
Если таких строк нет, остановись. Скажи, что в правилах штаба не указано, где лежат задачи отделов, и предложи дописать по строке на отдел в формате выше. Пути не угадывай.
Для каждого отдела прочитай его файл правил и задачи:
- локальные файлы: tasks/*.md, кроме README.md и _template.md;
- внешний источник (например GitHub Issues через gh): читай оттуда, если доступно;
- если источник недоступен, запомни отдел как «не прочитано» с причиной.
Если задач нет ни в одном отделе, остановись: фактов для ретро недостаточно.
Разложи задачи недели:
- «Сделано»: статус «принято», дата приёмки внутри недели;
- «Застряло»: заблокированные, просроченные, без движения всю неделю;
- «Снято»: снятые на этой неделе, с причиной.
Найди повторы: один и тот же блокер, одинаковый тип работы или одно решение человека, которое ждут несколько задач. Повтор это минимум два случая, иначе не пиши.
Запиши файл tasks/retro-<ГГГГ>-W<NN>.md в штабе. Если папки tasks/ нет, создай её.

Файл ретро

# Ретро <ГГГГ>-W<NN> · <дата начала>..<дата конца>

## Сделано
- <отдел> · <задача>: <результат> · [файл](../../corp-learn/tasks/<файл>.md)

## Застряло
- <отдел> · <задача>: <блокер или с какой даты стоит> · <ссылка>

## Снято
- <отдел> · <задача>: <причина> · <ссылка>

## Повторяется
- <что повторяется>: <ссылки на 2+ задачи>

## Не прочитано
- <отдел>: <причина>

Read the full file on GitHub · 66 lines

Files

What ships with it

2 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.

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.

27d ago Changed · -48 lines · +36 tokens per session b228e66115e6
1mo ago First seen · 114 lines · 39 tokens per session scan A 0bd59b35c83e

Subscribe to this mod's changes

retro is a skill published in the GitHub repository serejaris/personal-corp-os (238 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 862 once invoked, about $0.0003 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 2026-08-30.

Claude Code Planning Project management agentic-workflows ai-agents claude-code-skills open-source skills

milestone-runner

Use when asked to "run milestones", "execute EXECUTIONPROMPTS.md", "continue the milestone sequence", "run independent milestones in parallel", "merge the stack", or "reconcile M5" after prior work changes the current design. Not for generating plan files; use plan-prompts. Not for repairing one stack; use stacked-prs.

Mathews-Tom/armory · 76 tokens

task-decomposer

Produces phased task boards from feature requests: dependency-mapped work items, parallelization flags, risk flags, edge cases, test matrices. Triggers on: "decompose this feature", "task breakdown with dependencies", "phased implementation plan", "work breakdown structure". NOT for discovering which decisions are…

Mathews-Tom/armory · 81 tokens

project-context-setup

Scaffolds per-repository agent context so coding agents share the same issue tracker rules, triage label vocabulary, domain glossary, ADR layout, and handoff conventions. Triggers on: "set up project context", "configure agent docs", "create CONTEXT.md", "setup agent workflow", "agent issue tracker setup", "triage…

Mathews-Tom/armory · 109 tokens

github

GitHub CLI operations via gh for issues, PRs, Actions, releases, and REST/GraphQL API with --json/--jq parsing. Triggers on: "create an issue", "submit a PR", "check CI status", "why did CI fail", "merge a PR", or pasted GitHub URLs.

Mathews-Tom/armory · 74 tokens

slack

Slack workspace integration: 9 on-demand scripts (post, read, delete, search, stream, react, upload, channels, users) + dual-token support + RTS API search + chat streaming + AI Block Kit + Session Bridge + Claudicle unified launcher (Claude Agent SDK, soul engine, three-tier memory).

tdimino/claude-code-minoan · 67 tokens

crm-cleanup

A CRM data-cleanup workflow for finding inactive deals, duplicate contacts, and missing fields. A CRM is software used to manage customers, contacts, sales opportunities, and their activity history.

ilyautov/small-business-ru · 63 tokens