Menu
Validate omo plugin integrity — structure, frontmatter, script permissions, version consistency. Activate when #st appears anywhere in the user message.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Review the current diff, run the narrowest useful verification, and summarize remaining release risk. Activate when #sc appears anywhere in the user message.
Show unified omo status dashboard — boulder, ralph-loop, tasks, teams, and memory state at a glance. Activate when #ss appears anywhere in the user message.
Check if README.md and user guide reflect current project state — philosophy, features, agent models, skill list. Fix any drift. Activate when #sync appears anywhere in the user message.
Full release pipeline — commit, push, tag, GitHub release, marketplace version sync. Activate when #rel appears anywhere in the user message.
Triage a failure by capturing symptoms, narrowing reproduction, isolating likely files, and choosing the smallest useful verification loop. Activate when #bh appears anywhere in the user message.
Multi-perspective code review on the current diff or specified files. Examines correctness, security, performance, maintainability, and scope creep. Activate when #dr appears anywhere in the user message.
| name | self-test |
| description | Validate omo plugin integrity — structure, frontmatter, script permissions, version consistency. Activate when #st appears anywhere in the user message. |
| argument-hint | |
| disable-model-invocation | false |
| allowed-tools | Read, Glob, Grep, Bash |
Run omo plugin self-test.
Phase 1 — Structure check:
.claude-plugin/plugin.json exists and is valid JSON..claude-plugin/marketplace.json exists and is valid JSON.skills/, agents/, scripts/, templates/, examples/ directories exist.Phase 2 — Version consistency:
plugin.json.marketplace.json (metadata.version and plugins[0].version).scripts/check-version.sh exists, run it and report the result.Phase 3 — Skill validation:
For each directory in skills/:
SKILL.md exists.name, description, allowed-tools.name field matches the directory name.Phase 4 — Agent validation:
For each .md file in agents/:
name, description, tools, model, maxTurns.model is one of: haiku, sonnet, opus.Phase 5 — Script validation:
For each .sh file in scripts/:
#!/usr/bin/env bash or #!/bin/bash).shellcheck is available, run it on each script and report warnings.Phase 5.5 — Hooks validation:
hooks/hooks.json exists.Stop, SessionStart, Notification, SubagentStop, TeammateIdle, TaskCompleted, and PreCompact hook events.scripts/.Phase 5.6 — Config validation:
.omo/config.json exists, run bash scripts/validate-config.sh and report the result..omo/config.json does not exist, report as SKIP (config is optional).category: field matches a category defined in the config.Phase 6 — Report:
Summarize results:
omo self-test results
=====================
Plugin version: X.Y.Z
Structure: PASS/FAIL
Versions: PASS/FAIL (details if fail)
Skills (N): PASS/FAIL (details if fail)
Agents (N): PASS/FAIL (details if fail)
Scripts (N): PASS/FAIL (details if fail)
Hooks: PASS/FAIL/SKIP (details if fail)
Config: PASS/FAIL/SKIP (details if fail)
Overall: PASS / FAIL (N issues)
If any check fails, list each failure with enough detail to fix it.