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/octo-develop)<a href="https://agentmods.dev/commands/nyldn/claude-octopus/octo-develop"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/octo-develop/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/octo-develop"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/octo-develop.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 | $0.00013 | $0.01570 |
| Opus 5 | $0.00006 | $0.00785 |
| Sonnet 5 | $0.00003 | $0.00314 |
| Haiku 4.5 | $0.00001 | $0.00157 |
Grade B, and why
octo-develop scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
helper="$(find "${HOME}/.claude/plugins/cache" "${HOME}/Library/Application Support/Claude" "${LOCALAPPDATA:-/dev/null}/Claude" "${XDG_DATA_HOME:-${HOME}/.local/share}/Claude" -maxdepth 8 -path "*/nyldn-plugins/octo/*/sc Copies of this mod
1 near-identical copy found in the catalogue:
- develop — 98% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop - Development Phase 🛠️
Load skills/blocks/engineering-method-selection.md from the installed plugin
and apply only the methods relevant to this task. Preserve this entry point's
execution contract and output format. Read referenced skills as instructions;
do not invoke the current command recursively or add provider calls from a seat.
🤖 INSTRUCTIONS FOR CLAUDE
MANDATORY COMPLIANCE — DO NOT SKIP
When the user explicitly invokes /octo:develop, you MUST execute the structured workflow below. You are PROHIBITED from doing the task directly, skipping the development phase with quality gates, or deciding the task is "too simple" for this workflow. The user chose this command deliberately — respect that choice.
EXECUTION MECHANISM — NON-NEGOTIABLE
You MUST execute this command via the Bash tool calling orchestrate.sh develop. You are PROHIBITED from:
- Using
Skill(skill: "octo:develop")because it resolves back to this file and loops - Using
Skill(skill: "flow-develop", ...)because that internal name is not resolvable by the Skill tool - Using the Agent tool, WebFetch, Read, or Grep as a substitute for multi-provider dispatch
- Skipping
orchestrate.shcalls because "I can do this faster directly" - Implementing the task using only Claude-native tools
Multi-LLM orchestration is the purpose of this command. If you execute using only Claude, you've violated the command's contract.
When the user invokes this command (e.g., /octo:develop <arguments>):
Preflight — Ensure plugin root is resolvable (run via Bash tool FIRST):
OCTO_ROOT="${HOME}/.claude-octopus/plugin"
if [[ ! -x "$OCTO_ROOT/scripts/orchestrate.sh" ]]; then
helper="$OCTO_ROOT/scripts/helpers/ensure-plugin-root.sh"
if [[ ! -x "$helper" ]]; then
helper="$(find "${HOME}/.claude/plugins/cache" "${HOME}/Library/Application Support/Claude" "${LOCALAPPDATA:-/dev/null}/Claude" "${XDG_DATA_HOME:-${HOME}/.local/share}/Claude" -maxdepth 8 -path "*/nyldn-plugins/octo/*/scripts/helpers/ensure-plugin-root.sh" -print -quit 2>/dev/null)"
fi
[[ -x "$helper" ]] && bash "$helper" >/dev/null 2>&1 || true
fi
test -x "$OCTO_ROOT/scripts/orchestrate.sh" && echo "plugin-root:ok" || echo "plugin-root:missing"
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.
- yesterday Changed · +5 lines 13287e6ec1d0
- 5d ago First seen · 154 lines · 13 tokens per session scan B 174425158490
octo-develop is a command published in the GitHub repository nyldn/claude-octopus (4,056 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,570 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
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.
sparc-refinement-optimization-mode
🧹 Optimizer - You refactor, modularize, and improve system performance. You enforce file size limits, dependenc...
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.
checklist
Generate a custom checklist for the current feature based on user requirements.