Command Claude Code
Show current OMO model assignments in markdown tables and flag inconsistent, duplicate, or stale assignments.
not rated 6
changed 1mo ago A 18 tokens
original MIT
session-id
02Command Claude Code
Copy the invoking session ID to clipboard (no LLM round-trip).
not rated 6 2d ago A 14 tokens
original MIT
session-info
03Command Claude Code
Copy project path, session title, and session ID to clipboard (no LLM round-trip).
not rated 6 2d ago A 19 tokens
original MIT
vscode
04Command Claude Code
Open VS Code in the current project/worktree directory.
not rated 6 2d ago A 10 tokens
original MIT
Skill Claude CodeCodex
Atlas-level review orchestration handler. Manages the complete review workflow — delegates review tasks, processes findings, enforces cycle limits, and prevents loops. Loaded by the orchestrator when REVIEW-ENFORCER fires.
not rated 6
changed 1mo ago A 47 tokens
original MIT
debate
06Skill Claude CodeCodex
Structured adversarial analysis protocol. Quick single-agent modes (challenge, panel, pre-mortem, red team) plus a decision-review protocol where one agent proposes, one critiques, the proposer revises, and a binding/advisory judge panel decides ADOPT/REVISE/REJECT/ESCALATE.
not rated 6
changed 17d ago A SkillSpector: pass 67 tokens
original MIT
deployment
07Skill Claude CodeCodex
Infrastructure and deployment helper for server setup, port management, Docker/docker-compose, local services, and deployment automation. Maintains port registry to avoid conflicts.
not rated 6 2d ago D 32 tokens
original MIT
merge-agent
08Skill Claude CodeCodex
Safely merge a worktree branch into main with strict local state tracking, lock discipline, and deterministic rollback.
not rated 6 2d ago A 0 tokens
original MIT
parallel-dev
09Skill Claude CodeCodex
Skill "parallel-dev" from EZotoff/ez-omo-config, covering parallel-dev, should i parallelize? decision framework, mandatory preconditions (all must be yes), risk assessment (proceed if acceptable) and decision matrix.
not rated 6 2d ago A 0 tokens
original MIT
Skill Claude CodeCodex
Patch the live OpenCode binary with a minimal fix. Use when fixing bugs in OpenCode's Go/TypeScript binary — checkout the exact live version, apply the fix, build, install, and test. NEVER build from dev branch to patch a stable release.
not rated 6
changed 26d ago A 53 tokens
original MIT
Skill Claude CodeCodex
Reader-first writing for any deliverable a human reads to understand a result: HTML reports, MD design docs, debate-result summaries, survey dashboards, executive briefs, handoff notes, panel-review syntheses. Writes for a reader who has NOT read the preceding material. NOT for: bug reports, incident reports, status…
not rated 6
changed 27d ago A SkillSpector: pass 80 tokens
original MIT
Skill Claude CodeCodex
Register a new retryable error pattern in the error retry registry. Use when encountering errors that should trigger automatic retry.
not rated 6 2d ago A 28 tokens
original MIT
Skill Claude CodeCodex
Automated code review agent that analyzes git diffs and returns structured findings in CRITICAL/WARNING/INFO format. Loaded by sub-agents tasked with reviewing code changes.
not rated 6
changed 1mo ago A 38 tokens
original MIT
session-id
14Skill Claude CodeCodex
Copy the current OpenCode session ID to clipboard. Triggers on /session-id.
not rated 6 2d ago A 20 tokens
original MIT
Skill Claude CodeCodex needs its repo
Safety-critical operational pipeline for analyzing and executing OpenCode/OMO updates with explicit approval, patch preservation, rollback capability, and evidence-state discipline.
not rated 6
changed 26d ago A SkillSpector: warn 33 tokens
original MIT
wisdom
16Skill Claude CodeCodex
Primary runtime memory skill for institutional knowledge, operational facts, patterns, and decisions. Use for ALL knowledge queries including deployment, config, and infrastructure.
not rated 6
changed 17d ago A 32 tokens
original MIT
computer-use
17Skill Claude CodeCodex
OS-level computer use on the local X11 desktop via the cua-driver daemon: screenshots, AT-SPI element trees, background (co-work) mouse/keyboard input, and window management for NATIVE applications only. Use for native GUI apps without APIs, OS dialogs, and desktop automation; NOT for any browser/web task (use…
not rated 6 2d ago A 82 tokens
original MIT
add-provider
18Skill OpenCode
MUST USE when adding or changing models/providers in this repo's OpenCode config: new provider blocks, new model entries, enabledproviders edits, fallback chains, smallmodel / agent.title.model / OMO agent model assignments, or provider auth wiring. Encodes the checklist that prevents the six recurring setup failure…
not rated 6 2d ago A 93 tokens
original MIT
Command Claude Code
Specialist design review — draft, then critique, then challenge.
not rated 6 2d ago A 12 tokens
original MIT
dual-review
20Command Claude Code
Dual-track review — functional correctness and design quality in parallel, then merge findings.
not rated 6 2d ago A 15 tokens
original MIT
escalate
21Command Claude Code
Binding three-judge escalation — when a stuck decision needs a verdict, not more discussion.
not rated 6 2d ago A 17 tokens
original MIT
handoff
22Command Claude Code
Emit a handoff artifact for this session (optionally specify a slug).
not rated 6 2d ago A 15 tokens
original MIT
Command Claude Code
Compare options — draft each independently, then judge them against each other.
not rated 6 2d ago A 13 tokens
original MIT
resume-from
24Command Claude Code
Boot this session from a handoff artifact (slug, latest, or path).
not rated 6 2d ago A 16 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: