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.
npx agentmods add skills/lmanchu/iris-system/retronpx skills add lmanchu/iris-system --skill retrogit clone --depth 1 https://github.com/lmanchu/iris-systemWrote 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.
[](https://agentmods.dev/skills/lmanchu/iris-system/retro)<a href="https://agentmods.dev/skills/lmanchu/iris-system/retro"><img src="https://agentmods.dev/badge/skills/lmanchu/iris-system/retro.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00026 | $0.03080 |
| Opus 5 | $0.00013 | $0.01540 |
| Sonnet 5 | $0.00005 | $0.00616 |
| Haiku 4.5 | $0.00003 | $0.00308 |
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.
How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/retro — Weekly Engineering Retrospective
Generates a comprehensive engineering retrospective analyzing commit history, work patterns, and code quality metrics. Designed for a senior IC/CTO-level builder using Claude Code as a force multiplier.
User-invocable
When the user types /retro, run this skill.
Arguments
/retro— default: last 7 days/retro 24h— last 24 hours/retro 14d— last 14 days/retro 30d— last 30 days/retro compare— compare current window vs prior same-length window/retro compare 14d— compare with explicit window
Instructions
Parse the argument to determine the time window. Default to 7 days if no argument given. Use --since="N days ago", --since="N hours ago", or --since="N weeks ago" (for w units) for git log queries. All times should be reported in Pacific time (use TZ=America/Los_Angeles when converting timestamps).
Argument validation: If the argument doesn't match a number followed by d, h, or w, the word compare, or compare followed by a number and d/h/w, show this usage and stop:
Usage: /retro [window]
/retro — last 7 days (default)
/retro 24h — last 24 hours
/retro 14d — last 14 days
/retro 30d — last 30 days
/retro compare — compare this period vs prior period
/retro compare 14d — compare with explicit window
Step 1: Gather Raw Data
First, fetch origin to ensure we have the latest:
git fetch origin main --quiet
Run ALL of these git commands in parallel (they are independent):
# 1. All commits in window with timestamps, subject, hash, files changed, insertions, deletions
git log origin/main --since="<window>" --format="%H|%ai|%s" --shortstat
# 2. Per-commit test vs total LOC breakdown (single command, parse output)
# Each commit block starts with COMMIT:<hash>, followed by numstat lines.
# Separate test files (matching test/|spec/|__tests__/) from production files.
git log origin/main --since="<window>" --format="COMMIT:%H" --numstat
# 3. Commit timestamps for session detection and hourly distribution
# Use TZ=America/Los_Angeles for Pacific time conversion
TZ=America/Los_Angeles git log origin/main --since="<window>" --format="%at|%ai|%s" | sort -n
# 4. Files most frequently changed (hotspot analysis)
git log origin/main --since="<window>" --format="" --name-only | grep -v '^$' | sort | uniq -c | sort -rn
# 5. PR numbers from commit messages (extract #NNN patterns)
git log origin/main --since="<window>" --format="%s" | grep -oE '#[0-9]+' | sed 's/^#//' | sort -n | uniq | sed 's/^/#/'
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.
- 3d ago First seen · 341 lines · 26 tokens per session scan A 056121eeace5
retro is a skill published in the GitHub repository lmanchu/iris-system (5 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 3,080 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.
Other skills, from other repositories
code-review
Review code changes, pull requests, branches, commits, and diffs in the Terragrunt MCP Server. Use when asked for a code review, PR review, regression analysis, risk assessment, review comments, or merge-readiness check.
wendao
Internal guardian skill for creating and editing Wendao DocOS documentation.
super-claudio:discover-skills
Claude Code skill and plugin discovery fallback. Use when the user wants to find new Claude Code skills, plugins, or extensions — not general AI SaaS tools. Trigger on: "find a skill for X", "is there a skill that can do X", "find me a plugin", "search for a skill", "I need a skill for X", "find Claude skills"…
research
Autonomous documentation research using docsearch CLI - inspired by karpathy/autoresearch.
bug-fix
Minimal, surgical fix for a reported defect with focused validation.
super-claudio:find-ai-tools
AI tool discovery skill. Use when the user wants to find, compare, or evaluate AI-powered web tools — especially when they care about whether a tool has a genuinely free tier without requiring a credit card. Trigger on: "find AI tools for X", "best free AI tools for X", "list the best video creation tools", "find free…