2,572 tagged codex, measured the same way as everything else here.
Browse within: ai-coding 192gemini 171opencode 88gemini-cli 80copilot 71academic-research 61claude-code-plugin 60coding-agent 60ai-assistant 58curriculum 52code-quality 50agentic-workflow 49knowledge-graph 48ccusage 47
Command
Run a structured codebase audit. Maps the architecture, assesses health (compliance, tests, docs), performs deep analysis (security, performance, code quality), and synthesizes a prioritized roadmap. Outputs land under docs/audit/ in this project. Phases 0-3 with human checkpoints between each phase. Use /audit-quick…
Command
Run a stage of the Stagecraft pipeline. Wraps the devteam CLI so you can dispatch a stage (PM brief, design, build, review, QA, deploy, etc.) from inside Claude Code. The CLI emits the role-specific prompt; you invoke the matching subagent (under .claude/agents/) to do the work.
Command
Auto-commit changes after a Spec Kit command completes.
Command
Create a feature branch with sequential or timestamp numbering.
Command
Initialize a Git repository with an initial commit.
Command
Drive a governed idea-to-PR Walter-OS delivery cycle with feature-state, planning, TDD, review, and human gates.
Command
Ingest a source (URL, file path, or pasted text) into the operator's LLM-maintained wiki at $WALTEROSHOME/wiki/. Reads the source, drafts a sources/ - .md page, identifies referenced entities (people / companies / tools / concepts), creates stub pages with [[wikilinks]], updates topic hubs, and appends to log.md.…
Command
Prepare and (in personal/ context) open a PR after the implementer is done. In work/ ([Company]), prepares everything but stops short of opening the PR.
Command Claude Code
Command "deploy" from nerviq/nerviq, covering pre-deploy and deploy.
Command Claude Code
Fix the issue described: $ARGUMENTS.
Command Claude Code
Run a focused security review using Claude Code's built-in security workflow.
Command
A command for managing a project Charter, a document that records the agreed requirements, initial scope, and acceptance criteria.
Command
A project-status command for an IPD-OMO development project. It reads the project's state file and reports progress, review status, team tasks, risks, and suggested decisions.
Command
A command that runs a staged technical review process involving quality, testing, architecture, and requirements checks before a release decision. IPD-OMO is the process named in the add-on; its specialized role names are not explained further in the input.
Command
Read .claude/skills/handoff/SKILL.md completely and dispatch its export workflow. Use any supplied command arguments only as the requested bundle path; preserve the skill's sourceagent, direct checks, optional verification, and safety boundaries.
Command
Export a Waybill Bundle by default, or import one when requested.
Command
Alias that exports by default or imports when requested.
Command
Compose the 11-semantic-role chain for the current COMPLICATED+ task and dispatch.
Command
Scaffold a new coding-os project non-interactively — the official agent recipe (TASK-359).
Command
Run a Scrumban retrospective for the period specified by $ARGUMENTS (default: 14 days).
Command Claude Code
A command that handles Velog, a blogging platform, through its MCP tools.
Command
Run a complete design audit of the current interface against CANON standards. Checks typography, color, spacing, motion, interaction, responsive behavior, accessibility, forms, depth, states, performance, and UX writing. Reports violations grouped by severity.
Command
Normalize the codebase to the CANON token system. Extract scattered values into design tokens for color, type, spacing, radius, shadow, z-index, motion. Replace ad-hoc values with references. Use when the codebase has drifted into magic numbers.
Command
Explain a CANON rule or decision in plain language with before/after examples.
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: