agentmods.dev

octo-km

octo-km is a command for Claude Code from CES-Ltd/Lumi. It costs 12 tokens per session (465 once invoked), scanned A, original, MIT.

A command for switching between development work mode and knowledge work mode. It records the selected mode in a local configuration file.

In plain words
What is it for?
Run it without an argument or with “on” to enable knowledge work mode, or with “off” to return to development work mode.
Why use it?
It avoids manually editing the mode setting when changing between coding tasks and knowledge-focused work.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

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

not rated 31repo 4mo ago A scan 12 tokens original MIT

Good fit Run it without an argument or with “on” to enable knowledge work mode, or with “off” to return to development work mode.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ces-ltd/lumi/octo-km
View source ↗ 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.

Clone the repo
git clone --depth 1 https://github.com/CES-Ltd/Lumi

Made for: Claude Code.

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-km

README.md
[![agentmods](https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-km/github.svg)](https://agentmods.dev/commands/ces-ltd/lumi/octo-km)
Your own site
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-km"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-km/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.

agentmods 80×15 button for octo-km

Your own site · 80×15
<a href="https://agentmods.dev/commands/ces-ltd/lumi/octo-km"><img src="https://agentmods.dev/badge/commands/ces-ltd/lumi/octo-km.svg" alt="Reviewed on agentmods" width="80" 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 465 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00465
Opus 5 $0.00006 $0.00233
Sonnet 5 $0.00002 $0.00093
Haiku 4.5 $0.00001 $0.00047

Measured 12d ago against content hash 8214a356bf3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

octo-km 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 12d 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-km.md · 58 lines

What it actually says

Knowledge Mode Toggle

Toggle between Dev Work Mode and Knowledge Work Mode.

Implementation Instructions

When this command is executed:

  1. Parse the argument:

    • No argument or "on": Switch to Knowledge Work mode (set knowledge_mode: true)
    • "off": Switch to Dev Work mode (set knowledge_mode: false)

  2. Check for config file:

    • Config file: .claude/claude-octopus.local.md
    • If file doesn't exist when switching, create it
    • Use bash test -f to check existence before reading

  3. Switch to Knowledge Work mode (no argument or "on"):

    • Create/update .claude/claude-octopus.local.md with YAML frontmatter
    • Set knowledge_mode: true
    • Confirm with emoji 🎓 and active personas

  4. Switch to Dev Work mode ("off"):

    • Create/update .claude/claude-octopus.local.md with YAML frontmatter
    • Set knowledge_mode: false
    • Confirm with emoji 🔧 and active personas

Usage

/octo:km         # Switch to Knowledge Work mode (default action)
/octo:km on      # Switch to Knowledge Work mode (explicit)
/octo:km off     # Switch to Dev Work mode (same as /octo:dev)

Two Work Modes

Dev Work Mode 🔧 (default)

  • Best for: Building features, debugging code, implementing APIs
  • Personas: backend-architect, code-reviewer, debugger, test-automator

Knowledge Work Mode 🎓

  • Best for: User research, strategy analysis, literature reviews
  • Personas: ux-researcher, strategy-analyst, research-synthesizer

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

Quick Switch

  • /octo:dev - Switch to Dev Work mode 🔧
  • /octo:km - Switch to Knowledge Work mode 🎓

Your mode choice persists across sessions.

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. 12d ago First seen · 58 lines · 12 tokens per session scan A 8214a356bf3a

Subscribe to this mod's changes

octo-km is a command published in the GitHub repository CES-Ltd/Lumi (31 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 465 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.

Productivityagent-frameworkagentsaiai-agentsanthropicclaude
Related

Other commands, from other repositories

evolve

Cluster related instincts into skills, commands, or agents.

sangrokjung/claude-forge · 13 tokens

suggest-automation

A command that reviews recent Git commits and project instructions to find work patterns that happen repeatedly.

sangrokjung/claude-forge · 20 tokens

instinct-import

Import instincts from teammates, Skill Creator, or other sources.

sangrokjung/claude-forge · 15 tokens

instinct-export

Export instincts for sharing with teammates or other projects.

sangrokjung/claude-forge · 13 tokens

context-stats

Display context window usage and token statistics.

travisjneuman/.claude · 7 tokens

run

Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.

travisjneuman/.claude · 19 tokens