Help us improve
Share bugs, ideas, or general feedback.
From octo
Overrides Claude Code's context to Knowledge Work mode for research and writing when auto-detection selects Dev. Use when non-code tasks like market analysis, strategy, or document creation are misclassified.
npx claudepluginhub nyldn/claude-octopus --plugin octoHow this skill is triggered — by the user, by Claude, or both
Slash command
/octo:skill-knowledge-workThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.
Auto-detects whether a user is in development (code) or knowledge (research/strategy) context by analyzing prompt terms and project structure. Replaces manual mode toggling.
Auto-routes context-gathering tasks to codebase exploration or external research workflows. Use for pre-implementation background.
Orchestrates AI coding workflows with self-correction loops, pre-flight discipline rules, and cross-agent support for Claude Code and other agents.
Share bugs, ideas, or general feedback.
Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. Cross-reference commands use installed skill names in Codex rather than
/octo:*slash commands. Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. For host tool equivalents, seeskills/blocks/codex-host-adapter.md.
Claude Octopus now auto-detects work context! The system analyzes your prompt and project to determine whether you're in a Dev Context (code-focused) or Knowledge Context (research/strategy-focused).
You typically don't need this skill - context is detected automatically when you use:
octo research X - Auto-detects dev vs knowledge researchocto build X - Auto-detects code vs document buildingocto review X - Auto-detects code vs document reviewUse ONLY when auto-detection is wrong:
/octo:km on
All subsequent workflows will use Knowledge Context until reset.
/octo:km off
All subsequent workflows will use Dev Context until reset.
/octo:km auto
Context detection returns to automatic mode.
/octo:km
Shows current mode (auto, knowledge, or dev).
When you use any octo workflow, context is detected by analyzing:
Prompt Content (strongest signal):
Project Type (secondary signal):
package.json, Cargo.toml, go.mod → Dev Context.md, .docx, .pdf files → Knowledge ContextExplicit Override (if set via /octo:km):
When workflows run, you'll see the detected context in the banner:
Dev Context:
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode
🔍 [Dev] Discover Phase: Technical research on caching patterns
Knowledge Context:
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode
🔍 [Knowledge] Discover Phase: Market analysis for APAC expansion
User: "octo research caching strategies for our Node.js API"
Claude: (auto-detects Dev Context from "Node.js API")
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode
🔍 [Dev] Discover Phase: Technical research on caching strategies
[Researches with technical/implementation focus]
User: "octo research market opportunities in healthcare AI"
Claude: (auto-detects Knowledge Context from "market opportunities")
🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode
🔍 [Knowledge] Discover Phase: Strategic research on healthcare AI market
[Researches with business/strategic focus]
User: "octo research React patterns"
Claude: (auto-detects Dev) 🔍 [Dev] Discover Phase...
User: "Actually, this is for a presentation. Force knowledge mode."
Claude: "Setting context override to Knowledge Mode."
/octo:km on
User: "octo research React patterns"
Claude: (uses override) 🔍 [Knowledge] Discover Phase... (focuses on trends, adoption, strategic implications)
User: "What context mode am I in?"
Claude:
Current mode: Auto-detection (no override set)
Last detected context: Dev (based on project having package.json)
To override: /octo:km on (force Knowledge) or /octo:km off (force Dev)
To return to auto: /octo:km auto
| Workflow | Focus |
|---|---|
octo research X | Technical implementation, libraries, code patterns |
octo build X | Code generation, architecture, tests |
octo review X | Code quality, security, performance |
| Agents | codex, backend-architect, code-reviewer, security-auditor |
| Workflow | Focus |
|---|---|
octo research X | Market analysis, competitive research, literature synthesis |
octo build X | PRDs, strategy docs, presentations, reports |
octo review X | Document quality, argument strength, completeness |
| Agents | strategy-analyst, ux-researcher, exec-communicator, product-writer |
After running knowledge workflows, export to professional formats:
Just say: "Export this to Word" or "Create a PowerPoint presentation"
| Command | Description |
|---|---|
/octo:km | Show current status (auto, on, or off) |
/octo:km on | Force Knowledge Context for all workflows |
/octo:km off | Force Dev Context for all workflows |
/octo:km auto | Return to auto-detection (default) |
Don't override if:
Override is for:
At the end of significant work sessions, extract learnings:
Store learnings in .claude-octopus/learnings/<date>-<summary>.json:
{
"date": "2026-03-21",
"task_type": "debugging",
"approach": "Traced the error from the test failure back to the API handler",
"outcome": "success",
"lesson": "Always check middleware ordering before investigating handler logic"
}
Each learning file captures: task_type, approach, outcome, and lesson.
At session start, check for relevant learnings:
.claude-octopus/learnings/ directory/octo:discover - Research workflow (auto-detects context)/octo:develop - Build workflow (auto-detects context)/octo:deliver - Review workflow (auto-detects context)/octo:docs - Document export (works in both contexts)