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/staged-review)<a href="https://agentmods.dev/commands/nyldn/claude-octopus/staged-review"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/staged-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/nyldn/claude-octopus/staged-review"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/staged-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00012 | $0.01228 |
| Opus 5 | $0.00006 | $0.00614 |
| Sonnet 5 | $0.00002 | $0.00246 |
| Haiku 4.5 | $0.00001 | $0.00123 |
Grade A, and why
staged-review 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 7d 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
92% identical to octo-staged-review — 6 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staged Review — Two-Stage Pipeline
🤖 INSTRUCTIONS FOR CLAUDE
MANDATORY COMPLIANCE — DO NOT SKIP
When the user explicitly invokes /octo:staged-review, you MUST execute the structured workflow below. You are PROHIBITED from doing the task directly, skipping the review phases, or deciding the task is "too simple" for this workflow. The user chose this command deliberately — respect that choice.
EXECUTION MECHANISM — NON-NEGOTIABLE
You MUST dispatch work to external providers (Codex, Antigravity, etc.) for this command. You are PROHIBITED from:
- ❌ Executing the entire task using only Claude-native tools
- ❌ Using a single Agent subagent instead of multi-provider dispatch
- ❌ Skipping provider dispatch because "I can handle this alone"
Multi-LLM orchestration is the purpose of this command. Single-model execution defeats its purpose.
🐙 CLAUDE OCTOPUS ACTIVATED — Two-Stage Review Pipeline
When the user invokes this command (e.g., /octo:staged-review or /octo:staged-review src/auth/):
Step 0: Detect governed-workflow mode (skip interactive prompts)
Before Step 1, check for governed mode. If a .todo/claude-octopus/ directory exists in the working tree (set up by the Cruisey octo pipeline), this review is running INSIDE the autonomous governed workflow — the human gate is CP3, not here. In that case:
- Skip the Step 1 "Review Scope" prompt — the scope is always the full working tree (nothing is committed before CP3). Proceed directly with
git diffof the working tree. - Skip the "Post-Completion — Interactive Next Steps" prompt — proceed straight to the next phase (CP2 council, or the gatekeeper) without asking.
test -d .todo/claude-octopus && echo "GOVERNED_MODE" || echo "STANDALONE_MODE"
If STANDALONE_MODE, run the interactive prompts below as normal. If GOVERNED_MODE, do NOT call AskUserQuestion at any point in this command.
Step 1: Determine Review Scope
(GOVERNED_MODE: skip this prompt — scope = working tree.) Standalone only:
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.
- 7d ago First seen · 125 lines · 12 tokens per session scan A 74c32c107dc7
staged-review is a command published in the GitHub repository nyldn/claude-octopus (4,062 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 1,228 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to octo-staged-review, differing in 6 lines, and is treated as a copy.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
extend
Capture a mid-PR sub-idea and implement it onto the current open PR's branch — no new branch, no new PR. Preserves Verify → Review → Deliver.
integrity
Verify the cognitive toolkit's internal consistency and memory accuracy. The toolkit makes claims about its own structure, and memory makes claims about the world. This command checks both.
review
Code review based on git diff. Reviews staged/unstaged changes or a specific commit range for bugs, security issues, and code quality.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.