retrospective

retrospective is a skill for Claude Code from Vimalk0703/shipworthy. It costs 59 tokens per session (2,873 once invoked), scanned A, original, MIT.

A post-work review process that examines a coding session for corrections, failed approaches, improvised steps, and successful methods, then proposes updates to project learnings.

In plain words
What is it for?
It is for reviewing multi-step feature work, recording what worked or failed, and improving project guidance and the effectiveness of related skills.
Why use it?
It turns lessons from completed work into notes that can help future sessions avoid repeating mistakes. It runs after the work is finished rather than interrupting it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; mentions Claude Code.

Part of the shipworthy plugin — 66 skills, 7 commands, 3 hooks shipped together

Good fit It is for reviewing multi-step feature work, recording what worked or failed, and improving project guidance and the effectiveness of related skills.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vimalk0703/shipworthy/retrospective
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 Vimalk0703/shipworthy --skill retrospective
Clone the repo
git clone --depth 1 https://github.com/Vimalk0703/shipworthy

Made for: Claude Code.

Or install shipworthy, the plugin that ships this one along with the rest of its 66 skills, 7 commands, 3 hooks.

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 retrospective

README.md
[![agentmods](https://agentmods.dev/badge/skills/vimalk0703/shipworthy/retrospective.svg)](https://agentmods.dev/skills/vimalk0703/shipworthy/retrospective)
Your own site
<a href="https://agentmods.dev/skills/vimalk0703/shipworthy/retrospective"><img src="https://agentmods.dev/badge/skills/vimalk0703/shipworthy/retrospective.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,873 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 $0.00059 $0.02873
Opus 5 $0.00030 $0.01437
Sonnet 5 $0.00012 $0.00575
Haiku 4.5 $0.00006 $0.00287

Measured 8d ago against content hash 26c6933595ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

retrospective 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 8d 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/meta/retrospective/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retrospective

Core Principle

You can't design a skill from nothing. You can only improve after doing work. Every conversation produces signal — corrections the user made, steps that were improvised, things that worked on first try. The retrospective extracts that signal and turns it into permanent improvements.

When to Run

  • User explicitly runs /retro
  • After completing a multi-turn feature build
  • When the user says something like "that went well" or "that was rough"
  • At natural session end (before writing session summary)

Never interrupt work to run a retrospective. Wait until the work is done.

The Retrospective Process

Phase 1: Extract Signals

Review the entire conversation and categorize every notable moment:

Signal Type What to Look For Example
Corrections User said "no", "not that", "wrong", "I meant..." "No, use PostgreSQL not SQLite"
Redone Work Something built, then rebuilt differently Built REST first, user wanted GraphQL
Improvised Steps Steps not in any plan that were needed Had to add CORS middleware — no skill covered it
First-Try Success Things that worked immediately, no corrections TDD flow produced passing tests on first run
Skill Hits Which Shipworthy skills were invoked and helped intent-to-spec caught missing requirements
Skill Misses Situations where a skill should have helped but didn't No skill warned about CORS for frontend+API
User Preferences Patterns in how the user wants to work Prefers explicit confirmation before database changes
Anti-Patterns Patterns that caused failures or wasted time Built with SQLite, had to redo with PostgreSQL
Captured Signals Auto-captured events from hooks (.shipworthy/.session-signals) 3 security warnings, 2 dependency additions, 5 commits

Phase 1.5: Read Captured Signals

If .shipworthy/.session-signals exists, read it. This file contains automatically captured events from hooks during the session — security warnings, dependency additions, git operations, pattern detections, fence violations.

Read the full file on GitHub · 230 lines

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. 8d ago First seen · 230 lines · 59 tokens per session scan A 26c6933595ba

Subscribe to this mod's changes

retrospective is a skill published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 2,873 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

hedgehog-planning-intake

Use on any core for first-run planning intake — Phase 0 runs the vendored BMAD-METHOD planning shelf, shared by every core, and Phase 1 (mining 04-prd.md into intent records plus the Add-ons/sync-and-remote-entities decision) is full-stack-app's and pwa-app's shared procedure — identical mechanics, a different…

skyf0xx/hedgehog · 0 tokens

bmad-product-brief

Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.

skyf0xx/hedgehog · 31 tokens

bmad-deep-recon

Decision-grade research, three ways: draft a deep-research prompt for the user to run in their own tool (ChatGPT, Gemini, Grok, Perplexity, …), process a finished research report — file it, distill a succinct cited summary with metadata that downstream skills consume without reprocessing — or run the research here…

skyf0xx/hedgehog · 167 tokens

hedgehog

Use when the user writes the word "Hedgehog" anywhere in a request, or has agreed to install the Hedgehog build discipline in a project that does not have it yet. Hedgehog builds prose as well as code — articles, essays, blog posts, tweets, threads, newsletters, announcements, and marketing or product copy of any…

skyf0xx/hedgehog · 0 tokens

conventional-commits

Use when uncommitted changes need to be split into atomic, conventional commits ordered for review. Triggers on "commit this", "make commits", "clean up commits", "commit the changes". In Hedgehog, each Loop step is already meant to be its own commit — this skill matters most when a Correction Protocol fast-forward…

skyf0xx/hedgehog · 88 tokens

hedgehog-contributing

Use when the user wants to contribute a fix or ROADMAP.md item back to the Hedgehog project itself (skyf0xx/hedgehog) rather than their own project. Triggers on "let's fix that in Hedgehog", "I want to contribute", "let's pick up a roadmap item", or when tweaker offers this at the end of a build and the user says yes.…

skyf0xx/hedgehog · 120 tokens