retro

A post-work reflection command that records what was learned from completed coding work. It can save reusable patterns, mistakes to avoid, and significant lessons in a learning registry.

In plain words
What is it for?
Use it after completing work to review the hardest parts, capture new insights, document failures, update the learning registry, and create skill files for important lessons.
Why use it?
It prevents useful discoveries and debugging lessons from being forgotten after a task is finished.

Command for Claude Code

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/danielpodolsky/ownyourcode/retro
Clone the repo
git clone --depth 1 https://github.com/DanielPodolsky/ownyourcode

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,007 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 $0.00014 $0.02007
Opus 5 $0.00007 $0.01004
Sonnet 5 $0.00003 $0.00401
Haiku 4.5 $0.00001 $0.00201

Measured 2d ago against content hash 345590b896b6, 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 2d 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.

.claude/commands/own/retro.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/own:retro

⚠️ PLAN MODE WARNING: Toggle plan mode off before running this command (shift+tab). OwnYourCode commands don't work correctly with plan mode.

Extract learnings from completed work and persist them for future reference.

Overview

This command is run after completing work (typically after /own:done). It:

  1. Reflects on what was learned
  2. Documents patterns worth reusing
  3. Records failures to avoid
  4. Updates the learning registry
  5. Generates skill files for significant learnings

"The junior who documents their failures outgrows the senior who repeats them."


Execution Flow

Phase 1: What Did You Just Complete?

"What did you just finish working on?"

If they just ran /own:done, reference that context.

Get:

  • Feature/task name
  • Domain (auth, forms, API, etc.)
  • Rough summary

Phase 2: Learning Extraction

Ask these questions to extract learnings:

Question 1: The Hard Part

"What was the hardest part of this work?"

Looking for:

  • Technical challenges overcome
  • Confusing concepts clarified
  • Time-consuming debugging
Question 2: The Insight

"What do you know now that you didn't know before you started?"

Looking for:

  • New understanding of a concept
  • Better approach discovered
  • "Aha!" moments
Question 3: The Pattern (if applicable)

"Did you discover or use a pattern that worked well? Something you'd want to reuse?"

Looking for:

  • Code patterns worth extracting
  • Approaches that solved problems elegantly
  • Techniques to remember
Question 4: The Failure (most valuable)

"Did you make any mistakes or hit any walls? What went wrong before it went right?"

Looking for:

  • Bugs that took time to find
  • Wrong approaches tried first
  • Misunderstandings that caused problems
Question 5: The Advice

"If you could go back and tell yourself one thing before starting this task, what would it be?"

This often captures the most actionable learning.


Phase 3: Categorize Learnings

Read the full file on GitHub · 329 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. 2d ago First seen · 329 lines · 14 tokens per session scan A 345590b896b6

Subscribe to this mod's changes

retro is a command published in the GitHub repository DanielPodolsky/ownyourcode (276 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 2,007 once invoked, about $0.0001 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 2026-08-30.