retro

retro is a skill for Claude Code, Codex from tslateman/duet. It costs 17 tokens per session (420 once invoked), scanned A, original, MIT.

A session retrospective that records technical lessons from completed work and identifies specific topics to consider next.

In plain words
What is it for?
Use it after a task to capture patterns, gotchas, open work, file-specific questions, and the health of the project's MEMORY.md file.
Why use it?
It preserves useful discoveries and unresolved risks instead of reducing the session to a list of actions.

Skill for Claude CodeCodex

Part of the duet plugin — 25 skills, 6 commands, 1 agent 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 skills/tslateman/duet/retro
Any agent
npx skills add tslateman/duet --skill retro
Clone the repo
git clone --depth 1 https://github.com/tslateman/duet

Made for: Claude Code, Codex.

Or install duet, the plugin that ships this one along with the rest of its 25 skills, 6 commands, 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.

agentmods badge for retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/tslateman/duet/retro.svg)](https://agentmods.dev/skills/tslateman/duet/retro)
Your own site
<a href="https://agentmods.dev/skills/tslateman/duet/retro"><img src="https://agentmods.dev/badge/skills/tslateman/duet/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 420 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 $0.00017 $0.00420
Opus 5 $0.00009 $0.00210
Sonnet 5 $0.00003 $0.00084
Haiku 4.5 $0.00002 $0.00042

Measured 4d ago against content hash c9632fc42426, 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 4d 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 · 53 lines

What it actually says

Session Retrospective

Overview

Reflect on the work just completed in this conversation. Extract insights, not summaries.

What I Learned

Identify 2-4 concrete technical insights from this session:

  • Patterns discovered or reinforced
  • Gotchas or surprises encountered
  • Techniques that worked well (or didn't)
  • Connections to other parts of the codebase

Focus on insights, not a summary of actions taken.

What to Think About Next

Surface 2-4 open threads worth considering:

  • Unfinished work or TODOs
  • Edge cases or risks not yet addressed
  • Potential improvements or refactors
  • Questions that came up but weren't resolved

Be specific—name files, functions, or concepts rather than speaking abstractly.

Memory Health Check

Before asking about persistence, check the current project's MEMORY.md:

  1. Read the file from the project's auto memory directory
  2. Count lines -- if over 50, note the size
  3. Scan for staleness signals:
    • Items containing "resolved", "fixed", "done", "completed"
    • Date references from more than 30 days ago
    • Sections that duplicate CLAUDE.md headers
  4. Report briefly: "MEMORY.md: [N] lines, [issues found or 'healthy']"

If issues are found, include them in the question to the user -- e.g., "MEMORY.md has 3 stale items. Want to prune them while persisting new insights?"


After generating the retro, ask the user if any insights are worth persisting to auto memory. Use AskUserQuestion with options like "Yes, update MEMORY.md", "Yes, and prune stale items", and "No, just this session".

If yes, read the current MEMORY.md from the project's auto memory directory and intelligently merge the new insights—don't duplicate existing points, add new ones under the appropriate sections.

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. 4d ago First seen · 53 lines · 17 tokens per session scan A c9632fc42426

Subscribe to this mod's changes

retro is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 7d ago), licensed MIT. It adds 17 tokens to every session and 420 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 2026-08-31.