o9k-dispatch
Dispatch an isolated sub-agent that returns only [RESULT]...[/RESULT]. Use for any search, lookup, 'does X exist?', 'find Y', calculation, or isolated writing — never do these inline when dispatch fits.
Best use case
o9k-dispatch is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Dispatch an isolated sub-agent that returns only [RESULT]...[/RESULT]. Use for any search, lookup, 'does X exist?', 'find Y', calculation, or isolated writing — never do these inline when dispatch fits.
Teams using o9k-dispatch should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/o9k-dispatch/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How o9k-dispatch Compares
| Feature / Agent | o9k-dispatch | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Dispatch an isolated sub-agent that returns only [RESULT]...[/RESULT]. Use for any search, lookup, 'does X exist?', 'find Y', calculation, or isolated writing — never do these inline when dispatch fits.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# o9k-dispatch ## TRIGGER **Always dispatch for:** - **Searching** — "does a spec exist?", "find the plan for X", "search the codebase for Y", "check if skill Z covers this", "read the docs for W", "is there already a file that does X?" — any exploration or lookup task - **Calculation or lookup** — deterministic, context-free - **Writing an isolated section or document** — no conversation history needed - **Writing or modifying code** — never write code directly in the main context. Pass the project ID and relevant node IDs (e.g. `.2 Codebase`) in the task so the sub-agent can sync them after completing the work. Always include in the task: `"Invoke superpowers:coding-discipline before writing code."` **Never dispatch for tasks that require knowing the conversation context.** The key rule for searching: if you're about to run `grep`, `find`, `read`, or `search_memory` to answer a question — dispatch instead. The sub-agent explores, you synthesize the result. ## STEP 1: Define the task Write out before dispatching: - INPUT: exactly what the sub-agent needs — no more, no less - TASK: what to do with the input - OUTPUT FORMAT: what to return - VERIFY (optional): a concrete shell command that proves completion (e.g. `npx tsc --noEmit`, `grep "pattern" file.ts`). Use for tasks that produce code or file changes. ## STEP 2: Dispatch Send the sub-agent ONLY this prompt — no conversation history, no project context unless the task explicitly requires it: --- Task: <TASK> Input: <INPUT> [If VERIFY set:] After completing the task, run: <VERIFY_CMD> Return your answer in exactly this format: [RESULT] <answer here> [/RESULT] [If VERIFY set:] [VERIFY_RESULT] pass | fail: <command output or error> [/VERIFY_RESULT] Max 200 words. Use the o9k-subagent skill. --- ## STEP 3: Inject result Take ONLY the content between [RESULT] and [/RESULT]. If [VERIFY_RESULT] is present: check pass/fail. On fail, report the verification error instead of declaring the task complete. Discard all sub-agent reasoning and preamble. Use the result directly in the main conversation.