Claude Octopus is an orchestration project that sends research, design, and coding tasks to Claude Code and other AI model providers so their results can be compared. Developers use it for multi-model work, disagreement detection, reviews, persistent context, and an optional workflow that moves from discovery through delivery. The catalogue entries are its commands, skills, agents, instructions, hooks, plugins, and settings.
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.
git clone --depth 1 https://github.com/nyldn/claude-octopusWrote 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/commands/nyldn/claude-octopus/retro)<a href="https://agentmods.dev/commands/nyldn/claude-octopus/retro"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/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 5.1 | $0.00015 | $0.01475 |
| Opus 5 | $0.00008 | $0.00737 |
| Sonnet 5 | $0.00003 | $0.00295 |
| Haiku 4.5 | $0.00002 | $0.00147 |
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.
This is a copy
95% identical to octo-retro — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retro — Engineering Retrospective from Git History
Your first output line MUST be: 🐙 Octopus Retrospective
Generate data-driven engineering retrospectives by mining git history. Surfaces commit patterns, contributor breakdown, hotspots, session analysis, and AI-assisted commit tracking.
Usage
/octo:retro # Last 7 days (default)
/octo:retro 24h # Last 24 hours
/octo:retro 14d # Last 14 days
/octo:retro 30d # Last 30 days
Instructions
When the user invokes /octo:retro, you MUST follow these steps exactly.
1. Parse Time Window
Accept an optional argument for the time window. Default to 7d if none provided.
Supported formats:
24h— last 24 hours (--since='24 hours ago')7d— last 7 days (--since='7 days ago')14d— last 14 days (--since='14 days ago')30d— last 30 days (--since='30 days ago')
Map the argument to a git --since value. If the argument does not match a supported format, warn the user and fall back to 7d.
2. Gather Git Data
Run the following git commands to collect raw data. Each command MUST be executed — do NOT skip any.
Commit list:
git log --oneline --since='<window>' --no-merges
LOC changes (lines added/removed per file):
git log --numstat --since='<window>' --no-merges --format=''
Contributor leaderboard:
git shortlog -sn --since='<window>' --no-merges
Hotspot analysis (files modified most often):
git log --format='' --name-only --since='<window>' --no-merges | sort | uniq -c | sort -rn | head -20
PR merge count (merge commits):
git log --oneline --since='<window>' --merges | wc -l
Commit timestamps for session detection:
git log --format='%at %H %s' --since='<window>' --no-merges
AI-assisted commit detection:
git log --since='<window>' --no-merges --format='%b' | grep -ci 'Co-Authored-By:'
Current user identification:
git config user.name
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 · 209 lines · 15 tokens per session scan A 90d4340d769b
retro is a command published in the GitHub repository nyldn/claude-octopus (4,056 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 1,475 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to octo-retro, differing in 3 lines, and is treated as a copy.
Other commands, from other repositories
composite-actions
Generate, review, secure, and test composite GitHub Actions following best practices — full repo scaffold, interview-driven generation, PR creation on existing repos, SHA pinning, secrets-as-inputs, job summaries, and actionlint validation.
worktree
Manage git worktrees for isolated feature development.
hotfix
Ship a fast branch-based P0 hotfix — diagnose, implement, open a ready-for-review PR, then verify + review after (deferred by design).
resume
Show the restored Continuity project state (frozen constraints, decisions, rejected paths, next step).
orient-commit
Draft a git commit message (what / why / findings) for review before committing.
sdlc-release
Release planning and rollout - versioning, staging, gradual deployment, rollback.