cleanup
01Command
Autonomous cleanup-loop iteration: discover ONE target → complete execution → verify → report. Runs stateless: derive from current tree; assume prior runs left it consistent.
Command
Autonomous cleanup-loop iteration: discover ONE target → complete execution → verify → report. Runs stateless: derive from current tree; assume prior runs left it consistent.
Command
Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.
Command
Release all packages at specified version.
Command
Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.
Command
Classify/label newly opened GitHub issues missing labels.
Skill Claude CodeCodex
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
Skill Claude CodeCodex
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
Skill Claude CodeCodex
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
Instructions file CodexOpenCode
Instructions for can1357/oh-my-pi, covering development rules, default context, package structure, github and code quality.
Plugin Claude Code
Minimal marketplace demonstrating the catalog format.
Agent
UI/UX specialist for design implementation, review, visual refinement.
Agent
⌥ Coding agent with the IDE wired in.
Agent
Generate AGENTS.md for current codebase.
Agent
Researches external libraries and APIs by reading source code. Returns definitive, source-verified answers.
Agent
Code review specialist for quality/security analysis.
Agent
MUST be used for exploratory codebase research, rapid code analysis, and broad pattern searches. Fast read-only scout returning compressed context for handoff.
Agent
Read-only security specialist for evidence-backed repository vulnerability discovery.
Agent
Worker agent: delegated tasks.
Skill Claude CodeCodex
First calendar skill.
Skill Claude CodeCodex
A skill with consecutive hyphens in the name.
Skill Claude CodeCodex
A skill with invalid characters in the name.
Skill Claude CodeCodex
A skill with a name that exceeds 64 characters.
Skill Claude CodeCodex
This skill has no description field.
Skill Claude CodeCodex
A skill with a name that doesn't match the directory.