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/debug)<a href="https://agentmods.dev/commands/nyldn/claude-octopus/debug"><img src="https://agentmods.dev/badge/commands/nyldn/claude-octopus/debug.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 | $0.00009 | $0.00262 |
| Opus 5 | $0.00005 | $0.00131 |
| Sonnet 5 | $0.00002 | $0.00052 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
debug 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 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.
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-debug — 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.
What it actually says
Octopus debug
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.
Load and follow
${HOME}/.claude-octopus/plugin/.claude/skills/skill-debug/SKILL.md and its
literal skills/blocks/debug-feedback-loop.md reference.
Treat --peer-review as an instruction to request one bounded independent review
through existing Octopus routing. Never interpolate the flag or user text into a
shell command. Natural-language independent-review requests have the same meaning.
Otherwise run on the current host with zero additional provider dispatches unless
an existing escalation policy both requires and permits review under the effective
preferences and billing limits. Risk alone does not authorize a paid call;
honor explicit host-only requests.
Finish with the structured reproduction record. complete requires the original
scenario to pass and temporary instrumentation to be removed. Use inconclusive
when the required environment was unavailable.
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 · -20 lines · +1 tokens per session 16846874b39b
- 5d ago First seen · 49 lines · 8 tokens per session scan A 7fdf096434fb
debug is a command published in the GitHub repository nyldn/claude-octopus (4,056 stars, last pushed today), licensed MIT. It adds 9 tokens to every session and 262 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to octo-debug, differing in 3 lines, and is treated as a copy.
Other commands, from other repositories
refactor
You are the Refactor Specialist, a rigorous code quality engineer who improves code structure, maintainability, and performance while preserving behavior. You never break working code - you make it better.
bugfix
TDD-driven bugfix workflow: tester writes failing test (RED) → developer fixes (GREEN) → developer refactors (REFACTOR) → reviewer validates. Accepts issue number, description, or both. Auto-creates PR unless --no-pr flag is passed.
bug-fix-tdd
Fix a bug using TDD: reproduce with a failing test first, then implement the fix, then verify. Prevents regressions.
bug
Reproduce then TDD-fix a ready-for-agent bug ticket in this checkout. Web bugs get a browser repro first.
speckit.bug.test
Validate that a previously fixed bug is resolved and record the verification report.
api-aqa-flow
Workflow for backend API test automation: TMS / Issue Tracker test cases → automated API tests, HITL-gated.