retro-engineer

A skill for running an engineering retrospective, a review of recent development work to find what went well and what should improve. It can examine one repository or compare work across projects and AI tools.

In plain words
What is it for?
Use it for weekly or sprint reviews, per-person contribution summaries, test-health trend analysis, or a broader review across repositories and AI-assisted tools.
Why use it?
It turns scattered development activity into a review of shipped work, delivery speed, test health, and areas for growth. This makes recurring problems and improvement opportunities easier to see.

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/code-saurabh/openskills/retro-engineer
Any agent
npx skills add CODE-SAURABH/OpenSkills --skill retro-engineer
Clone the repo
git clone --depth 1 https://github.com/CODE-SAURABH/OpenSkills

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,765 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 $0.00057 $0.05765
Opus 5 $0.00028 $0.02882
Sonnet 5 $0.00011 $0.01153
Haiku 4.5 $0.00006 $0.00577

Measured 2d ago against content hash ff419062e2ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

retro-engineer 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.

retro-engineer/SKILL.md · 689 lines

How it starts

The opening of the file, as written. The whole thing — 689 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retro Engineer Skill

Overview

This skill guides you through a thorough, structured engineering retrospective. It operates in two distinct modes:

  1. Team Retro (Per-Person) — Analyses a single repository, breaking down contributions by individual team members: what they shipped, velocity trends, test health, praise, and growth areas.
  2. Global Retro (Cross-Project) — Spans all repositories and AI-assisted tools, producing a macro-level view of productivity, AI tool effectiveness, cross-project trends, and organisational health signals.

When in doubt about which mode to run, ask the user:

Which retro mode would you like?

  • A) Team Retro — per-person breakdown for this repo/sprint
  • B) Global Retro — cross-project, all AI tools, all repos

Step 0: Environment & Context Detection

Before starting any retro, gather environment context:

# Determine current repo
REPO_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "non-git")
REPO_SLUG=$(basename "$REPO_ROOT" 2>/dev/null || echo "global")
CURRENT_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
TODAY=$(date +%Y-%m-%d)
WEEK=$(date +%Y-W%V)

echo "REPO: $REPO_SLUG"
echo "BRANCH: $CURRENT_BRANCH"
echo "DATE: $TODAY"
echo "WEEK: $WEEK"

Identify the retro time window. Default is the last 7 days (weekly retro). If the user specifies a sprint length (e.g. 2 weeks, 4 weeks), use that window.

# Default: last 7 days
SINCE="7 days ago"
# For a 2-week sprint: SINCE="14 days ago"
# Always confirm with user if unclear

Mode A: Team Retro (Per-Person Breakdown)

Step A1: Collect Commit History

# Full commit log for the retro window with author details
git log \
  --since="$SINCE" \
  --format="%H|%an|%ae|%ad|%s" \
  --date=short \
  | sort > /tmp/retro_commits.txt

# Count commits per author
git shortlog \
  --since="$SINCE" \
  -sne \
  | sort -rn > /tmp/retro_authors.txt

cat /tmp/retro_authors.txt

Step A2: Collect PR & Branch Activity

Read the full file on GitHub · 689 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 · 689 lines · 57 tokens per session scan A ff419062e2ca

Subscribe to this mod's changes

retro-engineer is a skill published in the GitHub repository CODE-SAURABH/OpenSkills (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 5,765 once invoked, about $0.0003 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

seo-image-gen

AI image generation for SEO assets: OG/social preview images, blog hero images, schema images, product photography, infographics. Powered by Gemini via nanobanana-mcp. Requires banana extension installed. Use when user says "generate image", "OG image", "social preview", "hero image", "blog image", "product photo"…

AgriciDaniel/claude-seo · 111 tokens

seo-audit

Full website SEO audit with parallel subagent delegation. Crawls up to 500 pages, detects business type, delegates to up to 15 specialists (8 always + 7 conditional), generates health score. Use when user says audit, full SEO check, analyze my site, or website health check.

AgriciDaniel/claude-seo · 64 tokens

obsidian-markdown

Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.

AgriciDaniel/claude-obsidian · 68 tokens

wiki-lint

Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…

AgriciDaniel/claude-obsidian · 79 tokens

ecommerce-landing-page

Audit and optimize e-commerce landing pages for conversion. CTA placement, trust signals, page structure, copy optimization, and A/B testing strategy for product pages, collection pages, and campaign landing pages.

nexscope-ai/eCommerce-Skills · 45 tokens

blog-google

Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature…

AgriciDaniel/claude-blog · 155 tokens