retro

retro is a command for coding agents from Vimalk0703/shipworthy. It costs 0 tokens per session (342 once invoked), scanned A, original, MIT.

A retrospective command that reviews a coding session and extracts lessons from corrections, changed approaches, improvised steps, and successful practices.

In plain words
What is it for?
Use it to review findings, save approved project learnings, suggest skill updates, and update the session record.
Why use it?
It helps turn experience from one session into improvements for future work instead of letting useful lessons disappear.

Command

Part of the shipworthy plugin — 41 skills, 7 commands, 6 agents, 3 hooks shipped together

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.

agentmods
npx agentmods add commands/vimalk0703/shipworthy/retro
Clone the repo
git clone --depth 1 https://github.com/Vimalk0703/shipworthy

Or install shipworthy, the plugin that ships this one along with the rest of its 41 skills, 7 commands, 6 agents, 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 retro

README.md
[![agentmods](https://agentmods.dev/badge/commands/vimalk0703/shipworthy/retro.svg)](https://agentmods.dev/commands/vimalk0703/shipworthy/retro)
Your own site
<a href="https://agentmods.dev/commands/vimalk0703/shipworthy/retro"><img src="https://agentmods.dev/badge/commands/vimalk0703/shipworthy/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00342
Opus 5 $0.00000 $0.00171
Sonnet 5 $0.00000 $0.00068
Haiku 4.5 $0.00000 $0.00034

Measured 3d ago against content hash d52f974de003, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

commands/retro.md · 41 lines

What it actually says

Before executing this command, output:

shipworthy › command: /retro — extracting session learnings


Run a retrospective on the current session.

Analyze this entire conversation and extract what can be learned to make the next session better.

Process

Invoke the retrospective skill and follow its full process:

  1. Extract signals from this conversation:

    • Corrections the user made ("no", "not that", "I meant...")
    • Work that was redone or changed approach mid-stream
    • Steps that were improvised (not in any plan or skill)
    • Things that worked perfectly on first try
    • Which Shipworthy skills fired and helped
    • Which situations had no relevant skill (skill gaps)
    • User preferences discovered through their feedback
  2. Map each signal to the relevant Shipworthy skill (or note the gap)

  3. Present a findings table for the user to review:

    • Each finding with type, description, proposed action
    • User approves/rejects each item
  4. Apply approved changes:

    • Save project learnings to .shipworthy/learnings/
    • Propose (but don't auto-apply) skill file updates
    • Suggest auto-memory entries for user-level preferences
  5. Update the session summary with retrospective results

Important

  • Only analyze what already happened — don't suggest new work
  • Be specific: "User corrected database choice from SQLite to PostgreSQL" not "There were some database discussions"
  • If nothing notable happened (quick fix session), say so: "Clean session, no learnings to capture"
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. 3d ago First seen · 41 lines · 0 tokens per session scan A d52f974de003

Subscribe to this mod's changes

retro is a command published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 342 tokens. 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.