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-auto)<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-auto"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-auto/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-auto"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-auto.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 | $0.00011 | $0.01949 |
| Opus 5 | $0.00005 | $0.00975 |
| Sonnet 5 | $0.00002 | $0.00390 |
| Haiku 4.5 | $0.00001 | $0.00195 |
Grade A, and why
octo-auto 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.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Router (/octo:auto)
Single entry point for all Claude Octopus workflows. Analyzes your natural language request and routes to the optimal workflow automatically.
/octo:auto research OAuth authentication patterns
/octo:auto debug the failing test in auth.ts
/octo:auto should we use Redis or Memcached?
/octo:auto write tests for the payment module
/octo:auto create a complete e-commerce platform
All /octo:* commands also work directly, bypassing the router.
EXECUTION CONTRACT (Mandatory)
When the user invokes /octo:auto <query> or says octo <query>, you MUST follow these steps in order:
STEP 1: Input Validation
If the query exceeds 500 characters, use only the first 500 characters for intent analysis. Pass the full original query to the target workflow.
STEP 2: Meta Command Check
If the query matches any of: help, list, commands, what can you do, capabilities, options, workflows:
- Display the Complete Workflow Menu (see STEP 5c) and STOP. Do not route.
STEP 3: Analyze Intent
Match the query against keywords below. Check categories in priority order — higher priority wins when intents conflict.
Priority 1 — Specialized Workflows (check first, highest specificity)
| Intent | Trigger Keywords | Routes To |
|---|---|---|
| Lifecycle | end-to-end, complete lifecycle, full workflow, entire project, whole system | octo:embrace |
| Parallel | parallel, team of teams, decompose, work packages, split into, multi-instance | octo:parallel |
| Specification | spec, nlspec, specification, requirements doc, define scope, write spec | octo:spec |
| Security | security audit, OWASP, vulnerability, pentest, threat model, CVE, attack surface | octo:security |
| TDD | TDD, test-driven, write tests, test first, unit test, test coverage | octo:tdd |
| Debug | debug, fix bug, troubleshoot, broken, error trace, stacktrace, failing, crash | octo:debug |
| Design | UI design, UX design, wireframe, mockup, design system, layout, prototype | octo:design-ui-ux |
| PRD | PRD, product requirements, product spec, feature requirements | octo:prd |
| Brainstorm | brainstorm, ideate, ideas, creative, thought experiment, what if | octo:brainstorm |
| Deck | presentation, slides, deck, pitch deck, slide deck | octo:deck |
| Docs | document, documentation, README, API docs, write docs, docstring | octo:docs |
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 · 200 lines · 11 tokens per session scan A 7971c13ecb1c
octo-auto is a command published in the GitHub repository CES-Ltd/Lumi (31 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 1,949 once invoked, about $0.0001 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 2026-08-30.
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.