agentmods.dev

octo-dev

octo-dev is a command for coding agents from CES-Ltd/Lumi. It costs 12 tokens per session (392 once invoked), scanned A, original, MIT.

A command that switches Claude Octopus, a coding-agent setup with multiple specialist roles, into software-development mode.

In plain words
What is it for?
Building features, implementing APIs, debugging, reviewing architecture and code, and working with test-driven development, a practice of writing tests alongside code.
Why use it?
It changes the agent’s configuration so development tasks are treated as the active focus instead of knowledge-oriented work.

Command

Part of the octo plugin — 10 skills, 47 commands shipped together

not rated 31 +1 3mo ago A scan 12 tokens original MIT
View the source file CES-Ltd/Lumi
Install

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.

agentmods
npx agentmods add commands/ces-ltd/lumi/octo-dev
Clone the repo
git clone --depth 1 https://github.com/CES-Ltd/Lumi

Or install octo, the plugin that ships this one along with the rest of its 10 skills, 47 commands.

Wrote 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.

agentmods badge for octo-dev

README.md
[![agentmods](https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-dev.svg)](https://agentmods.dev/commands/ces-ltd/lumi/octo-dev)
Your own site
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-dev"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 392 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00392
Opus 5 $0.00006 $0.00196
Sonnet 5 $0.00002 $0.00078
Haiku 4.5 $0.00001 $0.00039

Measured 5d ago against content hash 87f2a4ad9ec4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

octo-dev 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 5d 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.

resources/seed/octopus/commands/octo-dev.md · 60 lines

What it actually says

Dev Work Mode

Switch to Dev Work Mode, optimized for software development.

Implementation Instructions

When this command is executed:

  1. Check current mode:

    • Config file: .claude/claude-octopus.local.md
    • If file doesn't exist, user is already in Dev Work Mode (default)
    • Use bash test -f to check existence before reading

  2. Switch to Dev Work mode:

    • Create/update .claude/claude-octopus.local.md with YAML frontmatter
    • Set knowledge_mode: false
    • Confirm the switch with current mode details

  3. Show confirmation:

    • Display Dev Work Mode emoji (🔧)
    • List active personas
    • Suggest available commands (octo build, octo review, etc.)

Usage

/octo:dev        # Switch to Dev Work mode

What is Dev Work Mode?

Dev Work Mode 🔧 is optimized for:

  • Building features and implementing APIs
  • Debugging code and fixing bugs
  • Technical architecture and code review
  • Test-driven development

Personas: backend-architect, code-reviewer, debugger, test-automator, performance-engineer

Two Work Modes

Claude Octopus has two work modes:

  1. Dev Work Mode 🔧 (this mode)

    • For: Software development, code, technical tasks

  2. Knowledge Work Mode 🎓

    • For: User research, strategy analysis, literature reviews
    • Switch: /octo:km on

Both modes use the same AI providers (Codex + Gemini), just optimized with different personas.

Learn More

Run /octo:setup to configure your preferences and choose your default mode.

Changes

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.

  1. 5d ago First seen · 60 lines · 12 tokens per session scan A 87f2a4ad9ec4

Subscribe to this mod's changes

octo-dev is a command published in the GitHub repository CES-Ltd/Lumi (31 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 392 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.

Building agentsagent-frameworkagentsaiai-agentsanthropicclaude
Related

Other commands, from other repositories

setup

Full onboarding for a new project — runs /doctor diagnostics, then injects the CLAUDE.md template + nav-ref instrumentation + Zustand store exposure so the plugin works without the user having to read documentation.

Lykhoyda/rn-dev-agent · 41 tokens

run-action

Execute a learned Maestro flow ("action") by name with optional -e KEY=VALUE parameters. Looks the flow up via packages/rn-dev-agent-core/dist/learned-actions.js (same inventory as /rn-dev-agent:list-learned-actions), then replays it via cdprunaction — auto-repair-aware orchestration with structured RunRecords (GH.

Lykhoyda/rn-dev-agent · 72 tokens

test-feature

Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.

Lykhoyda/rn-dev-agent · 30 tokens

nav-graph

Extract, inspect, and query the app navigation graph — a complete map of all screens and navigators.

Lykhoyda/rn-dev-agent · 21 tokens

doctor

Diagnose installation health. Check Node, CDP bridge, rn-fast-runner (iOS), rn-android-runner (Android), maestro-runner, simulators, Metro, CDP, injected helpers, ffmpeg, physical devices, plugin version, Vercel rules sync. Reports what's missing — does NOT modify your project.

Lykhoyda/rn-dev-agent · 68 tokens

check-env

Check that the fenced React Native session, Metro, app target, and device inventory are ready for testing.

Lykhoyda/rn-dev-agent · 21 tokens