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/CES-Ltd/LumiWrote 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/ces-ltd/lumi/octo-debate)<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-debate"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-debate/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/ces-ltd/lumi/octo-debate"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-debate.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 | $0.00021 | $0.00568 |
| Opus 5 | $0.00010 | $0.00284 |
| Sonnet 5 | $0.00004 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
octo-debate 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 10d 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
89% identical to octo-debate — 16 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debate
Structured four-way AI debates between Claude, Sonnet, Gemini, and Codex.
🤖 INSTRUCTIONS FOR CLAUDE
MANDATORY COMPLIANCE — DO NOT SKIP
When the user explicitly invokes /octo:debate, you MUST execute the structured debate workflow below. You are PROHIBITED from answering the question directly, skipping the multi-provider debate, or deciding the topic is "too simple" for a four-way debate. The user chose this command deliberately — respect that choice.
EXECUTION MECHANISM — NON-NEGOTIABLE
You MUST dispatch work to external providers (Codex, Gemini, 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.
Execution
- Follow the
skill-debateinstructions (Steps 1-7) exactly. - Start with Step 1: check provider availability and display the visual indicator banner.
- Step 2: ask clarifying questions via AskUserQuestion before proceeding.
- Steps 3-5: parse arguments, set up debate folder, conduct rounds with all four participants (Gemini CLI, Codex CLI, Sonnet Agent, Claude/Opus).
- Steps 6-7: write final synthesis and present results to the user.
- Apply quality gates and cost tracking from
skill-debatethroughout.
Post-Completion — Interactive Next Steps
CRITICAL: After the debate completes, you MUST ask the user what to do next. Do NOT end the session silently.
AskUserQuestion({
questions: [
{
question: "The debate is complete. What would you like to do next?",
header: "Next Steps",
multiSelect: false,
options: [
{label: "Run another round", description: "Continue the debate with additional rounds"},
{label: "Act on the winner", description: "Proceed with the winning argument's recommendation"},
{label: "Debate a related topic", description: "Start a new debate on a follow-up question"},
{label: "Export the synthesis", description: "Save the debate results as a document"},
{label: "Done for now", description: "I have what I need"}
]
}
]
})
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.
- 10d ago First seen · 57 lines · 21 tokens per session scan A 0c69f64b8ef4
octo-debate is a command published in the GitHub repository CES-Ltd/Lumi (31 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 568 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to octo-debate, differing in 16 lines, and is treated as a copy.
Other commands, from other repositories
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
workflow-classify
Classify task size (S/M/L/XL) and recommend the appropriate workflow pipeline.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
sonarqube
Analyze SonarCloud quality issues for a specific PR.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.