retro

retro is a skill for Claude Code, Codex from uxname/LiteStack. It costs 78 tokens per session (684 once invoked), scanned A, original, MIT.

A session review that records mistakes, dead ends, wrong assumptions, and their causes in a project's documentation. It also defines a rule to help prevent each problem from happening again.

In plain words
What is it for?
Use it at the end of a work session to document failed commands, edited the wrong files, misunderstood conventions, or fixes that had to be redone.
Why use it?
It preserves lessons from development sessions so later coding agents do not repeat the same errors. It focuses on prevention rather than listing completed work.

Skill for Claude CodeCodex

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/uxname/litestack/retro
Any agent
npx skills add uxname/LiteStack --skill retro
Clone the repo
git clone --depth 1 https://github.com/uxname/LiteStack

Made for: Claude Code, Codex.

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/uxname/litestack/retro.svg)](https://agentmods.dev/skills/uxname/litestack/retro)
Your own site
<a href="https://agentmods.dev/skills/uxname/litestack/retro"><img src="https://agentmods.dev/badge/skills/uxname/litestack/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 684 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 $0.00078 $0.00684
Opus 5 $0.00039 $0.00342
Sonnet 5 $0.00016 $0.00137
Haiku 4.5 $0.00008 $0.00068

Measured 3d ago against content hash 2e2670bbfaac, 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.

.claude/skills/retro/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The point of a retro is future prevention, not a changelog. Capture what went wrong this session so the next agent — which reads docs/retro/* before touching code — does not repeat it. Successes are irrelevant here.

Step 1: Reconstruct what went badly this session

Look back over the session and list only the mistakes, dead ends, and wrong assumptions. Concrete signals to mine:

  • Commands/tests that failed and why (quote the error).
  • Wrong files edited, paths assumed that didn't exist, wrong submodule touched.
  • Doc/convention misread (e.g. wrong Biome quote style, skipped npm run check, used --no-verify).
  • A fix that had to be redone, reverted, or that broke something else.
  • Time lost to a wrong mental model of how the code works.

If the session was genuinely clean (no mistakes), say so to the user and do not write an empty retro file. A retro with no problems is noise.

Step 2: Pick the area and a filename

Decide area: backend (only backend/ touched), frontend (only frontend/), meta (only meta-repo files), or cross (spanned both submodules or the seam between them).

date +%F        # use this real date — never guess

Filename: docs/retro/<YYYY-MM-DD>-<short-slug>.md. Slug = session topic, kebab-case. If a file for today's topic already exists, append to it rather than overwriting.

Step 3: Write the file

Copy docs/retro/TEMPLATE.md exactly. Fill every section:

  • What went badly — one concrete fact per bullet.
  • Root cause — the underlying reason, not the symptom.
  • Rule — do this next time — one imperative line per problem. This is the payload the next agent acts on. Make it specific and checkable (e.g. "Run npm run check in frontend/ before declaring done — lint alone skips knip/steiger").

Frontmatter date, topic, area, tags are mandatory — the reader subagent filters on them.

Step 4: Confirm

Tell the user the path written and a one-line summary of the rules captured. Do not commit here — the /commit skill stages and commits docs/retro/ with the rest of the session.

Read the full file on GitHub · 59 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. 3d ago First seen · 59 lines · 78 tokens per session scan A 2e2670bbfaac

Subscribe to this mod's changes

retro is a skill published in the GitHub repository uxname/LiteStack (2 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 684 once invoked, about $0.0004 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

article-writing

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

affaan-m/ECC · 57 tokens

ljg-learn

Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…

lijigang/ljg-skills · 113 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

code-documenter

Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.

zebbern/claude-code-guide · 39 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens

grid-ctf-ops

Operational knowledge for the gridctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging gridctf strategies.

greyhaven-ai/autocontext · 42 tokens