Claude-skill-registry-data mission-solo

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

install

source · Clone the upstream repo

git clone https://github.com/majiayu000/claude-skill-registry-data

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry-data "$T" && mkdir -p ~/.claude/skills && cp -r "$T/data/mission-solo" ~/.claude/skills/majiayu000-claude-skill-registry-data-mission-solo && rm -rf "$T"

manifest: data/mission-solo/SKILL.md

source content

/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:

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

Then inform user and suggest switching to orchestrated mode.