mission-solo

HOUSTON executes feature tasks directly. No agents. Best for small features (1-3 tasks).

Stars 163

Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/mission-solo

SKILL.md

/mission-solo - Direct Execution

HOUSTON executes tasks directly without spawning agents. Fast for small features, but context fills quickly.

Warning

HOUSTON: Solo mode fills context fast. Only use for:
         - Small features (1-3 tasks)
         - Quick demos
         - Debugging a single task

         For larger work, use /mission-orchestrated.

The Process

Load feature - Run bd show FEATURE_ID to get feature details and tasks
Activate feature - Run bd update FEATURE_ID --status in_progress
Get next task - Run bd list --parent FEATURE_ID --status open (pick highest priority)
Scout - Spawn Explore agent to gather codebase context (facts only, no suggestions)
Execute task - Implement the work directly using scout context (write code, run tests)
Mark complete - Run bd close TASK_ID
Loop - Repeat steps 3-6 until no tasks remain
Complete feature - Run bd close FEATURE_ID

On Completion

HOUSTON: Feature complete. {N} tasks executed.
         Run /capcom for status summary.

On Blocker

If you hit a blocker you cannot resolve:

bash

bd create -t bug --title "Blocker: description" --blocks TASK_ID

Then inform user and suggest switching to orchestrated mode.