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
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add nyldn/claude-octopus/plugin install octoWrote 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/nyldn/claude-octopus/debate-kickoff)<a href="https://agentmods.dev/skills/nyldn/claude-octopus/debate-kickoff"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/debate-kickoff/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/skills/nyldn/claude-octopus/debate-kickoff"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/debate-kickoff.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 | $0.00037 | $0.00400 |
| Opus 5 | $0.00018 | $0.00200 |
| Sonnet 5 | $0.00007 | $0.00080 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
debate-kickoff 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 4d 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.
What it actually says
Debate Kickoff (Starter Pack)
Turn a loosely stated decision ("Redis or Memcached?", "monorepo vs polyrepo") into a well-formed multi-model debate.
When to use
The user has a two-or-more-sided technical decision and wants adversarial perspectives from different model families rather than one model's opinion.
Steps
- Extract the motion. Restate the user's question as a single debatable proposition (for example: "This project should use Redis over Memcached for session storage"). Confirm silently from context; do not interrogate the user.
- Check seats. Run
${CLAUDE_PLUGIN_ROOT}/scripts/helpers/check-providers.shand note which providers are available. A debate needs at least two seatable non-Claude providers for cross-lab disagreement; if only Claude is available, say so and offer a single-model pro/con instead. - Assign sides. Give each available provider an explicit stance (affirmative, negative, or skeptic). Prefer cross-lab pairings (for example Codex affirmative, Antigravity negative) so disagreement is structural, not stylistic.
- Launch. Invoke
/octo:debatewith the motion and the side assignments. Display the standard Octopus banner with provider indicators before dispatch. - Synthesize. After rounds complete, summarize where the models converged, where they genuinely disagreed, and give one recommendation with the strongest surviving argument.
Guardrails
- External seats cost money; state the expected cost band from the CLAUDE.md cost table before dispatch.
- Never fabricate a provider's position. If a seat fails, report the failure and continue with the remaining seats.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 27 lines · 37 tokens per session scan A 0408325c9f4e
debate-kickoff is a skill published in the GitHub repository nyldn/claude-octopus (4,058 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 400 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
ai-context
Generates, updates, and audits AGENTS-first AI IDE context files. Builds canonical AGENTS.md plus thin bridges for Claude Code, Cursor (modern .cursor/rules/.mdc), Copilot, Cline (.clinerules/ directory), Windsurf, Gemini CLI, Codex CLI, and OpenCode. Use for creating, regenerating, fixing, or promoting context files…
architecture
This skill should be used when managing Architecture Decision Records or C4 diagrams.
linear-fetch
This skill should be used when a user input contains a Linear issue reference (e.g., SOL-39 or linear.app/.../issue/ ) and the downstream agent needs the screenshots embedded in the issue as visual context.
invoice
This skill should be used when the founder wants to get paid through their own Stripe account: list who owes them, create and send an invoice behind a human-approval preview, or chase an overdue one. Test-mode only in v1.
legal-generate
This skill should be used when generating draft legal documents for a project or company. It gathers company context interactively, invokes the legal-document-generator agent, and writes markdown output.
agent-native-audit
This skill should be used when conducting a scored agent-native architecture review. It launches 8 parallel sub-agents to audit action parity, context injection, CRUD completeness, capability discovery, and prompt-native features.