can1357

16 mods across 2 repositories, 36k stars between them.

cleanup

01

can1357/oh-my-pi

Command Claude Code

Autonomous cleanup-loop iteration: discover ONE target → complete execution → verify → report. Runs stateless: derive from current tree; assume prior runs left it consistent.

not rated 36k +727 today A 0 tokens original MIT

fix-issues

02

can1357/oh-my-pi

Command Claude Code

Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.

not rated 36k +727 today A 0 tokens original MIT

release

03

can1357/oh-my-pi

Command Claude Code needs its repo

Release all packages at specified version.

not rated 36k +727 today A 0 tokens original MIT

review-prs

04

can1357/oh-my-pi

Command Claude Code

Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.

not rated 36k +727 today A 0 tokens original MIT

triage

05

can1357/oh-my-pi

Command Claude Code

Classify/label newly opened GitHub issues missing labels.

not rated 36k +727 today A 0 tokens original MIT

can1357/oh-my-pi

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…

not rated 36k +727 today A SkillSpector: pass 77 tokens original MIT

system-prompts

07

can1357/oh-my-pi

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.

not rated 36k +727 today A Snyk: passSkillSpector: pass 40 tokens original MIT

can1357/oh-my-pi

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…

not rated 36k +727 today A Snyk: passSkillSpector: pass 0 tokens original MIT

[object Object]

09

can1357/oh-my-pi

Agent Claude Code

⌥ Coding agent with the IDE wired in. Built by Stencil Labs.

not rated 36k +727 today A 8 tokens original MIT

init

10

can1357/oh-my-pi

Agent Claude Code

Generate AGENTS.md for current codebase.

not rated 36k +727 today A 10 tokens original MIT

reviewer

11

can1357/oh-my-pi

Agent Claude Code

Code review specialist for quality/security analysis.

not rated 36k +727 changed 26d ago A 10 tokens original MIT

scout

12

can1357/oh-my-pi

Agent Claude Code

MUST be used for exploratory codebase research, rapid code analysis, and broad pattern searches. Fast read-only scout returning compressed context for handoff.

not rated 36k +727 changed 4d ago A 33 tokens original MIT

security-reviewer

13

can1357/oh-my-pi

Agent Claude Code

Read-only security specialist for evidence-backed repository vulnerability discovery.

not rated 36k +727 changed 26d ago A 14 tokens original MIT

seance

14

can1357/oh-my-pi

Agent Claude Code

Read a historical session and nested transcripts to answer a consult.

not rated 36k +727 today A 15 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: