retro

retro is a skill for Claude Code, Codex from liwala/sheal. It costs 39 tokens per session (835 once invoked), scanned A, original, MIT.

A retrospective workflow for examining a completed AI coding session and extracting lessons for future work.

In plain words
What is it for?
Use it to review session data and static-analysis results, explain what went wrong or worked well, and create practical rules for later sessions.
Why use it?
It helps identify failure patterns, wasted effort, missing context, and tool choices that affected the session.

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

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/liwala/sheal/retro.svg)](https://agentmods.dev/skills/liwala/sheal/retro)
Your own site
<a href="https://agentmods.dev/skills/liwala/sheal/retro"><img src="https://agentmods.dev/badge/skills/liwala/sheal/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 835 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 $0.00039 $0.00835
Opus 5 $0.00019 $0.00417
Sonnet 5 $0.00008 $0.00167
Haiku 4.5 $0.00004 $0.00084

Measured 5d ago against content hash 14c48c17e087, 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 5d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Retrospective Skill

You are performing a deep retrospective analysis of a completed AI coding session. This is the self-healing loop: you're reviewing what happened and generating actionable rules to improve future sessions.

Step 1: Gather Data

Run the static analysis first. If a checkpoint ID was provided as an argument, use it. Otherwise, use the latest checkpoint.

sheal retro --format json [-c CHECKPOINT_ID]

Also load the session details to see the Entire.io summary:

sheal sessions --format json [-c CHECKPOINT_ID]

Step 2: Deep Analysis

With the static analysis and session data loaded, analyze the session deeply. Consider:

Failure Patterns

  • For each failure loop or Bash failure: why did it happen? Was it a wrong approach, missing context, environment issue, or normal iteration?
  • Could a pre-check have prevented it?
  • Was the agent stuck or making progress?

Effort Quality

  • Was the file churn productive iteration or wasted effort?
  • Were the right tools used? (e.g., using Bash when Read/Grep would have been better)
  • Was research done before implementation, or was the approach trial-and-error?

Missing Context

  • What information was missing at the start that caused problems later?
  • What should have been in CLAUDE.md, .cursorrules, or project documentation?
  • Were there assumptions that turned out wrong?

Workflow Improvements

  • What would make the next session smoother?
  • Are there recurring patterns that should become rules?
  • Should any health checks be added to sheal check?

Step 3: Generate Output

Present your analysis as a structured retrospective report:

Report Format

## Session Retrospective: [checkpoint-id]

### Summary
[1-2 sentence summary of what happened and how it went]

### Health Score: [X/100]
[Explain why this score, what went well, what didn't]

### Key Findings

#### What Went Well
- [thing 1]
- [thing 2]

#### What Could Be Improved
- [issue 1]: [why it happened] → [what to do differently]
- [issue 2]: [why it happened] → [what to do differently]

### Suggested Rules
[List specific rules that should be added to agent config files]

Read the full file on GitHub · 105 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. 5d ago First seen · 105 lines · 39 tokens per session scan A 14c48c17e087

Subscribe to this mod's changes

retro is a skill published in the GitHub repository liwala/sheal (86 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 835 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

ads-linkedin

Audit LinkedIn Ads measurement, Insight Tag and conversions, professional audiences, lead generation, ABM, creative, bidding, budgets, pacing, automation, and policy. Use for LinkedIn Ads, Campaign Manager, Insight Tag, Lead Gen Forms, Thought Leader Ads, ABM campaigns, or B2B paid media.

AgriciDaniel/claude-ads · 68 tokens

ads-launch

Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.

AgriciDaniel/claude-ads · 45 tokens

bun-test-mocking

Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.

secondsky/claude-skills · 25 tokens

api-response-optimization

Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.

secondsky/claude-skills · 36 tokens

plan-create

Create structured implementation plans for autonomous TDD development. Use for new features, multi-file changes, or anything requiring multiple steps or tests. Triggers on aspirational openers ("let's build", "let's start building", "I want to make", "I want an app that", "help me build"), capability lists ("users…

markshust/hcf · 171 tokens

blog-multilingual

One-command multilingual blog creation. Writes a blog post, translates it into user-specified languages, applies cultural adaptation, and emits hreflang tags, sitemap entries, and a CMS-ready language map. The complete write-to-publish pipeline for international content. Orchestrates blog-write, blog-translate…

AgriciDaniel/claude-blog · 130 tokens