Plugin Claude Code
Strip the sycophancy. Makes Claude honestly audit its own claimed-complete work against 17 named under-delivery patterns instead of polishing a summary over half-finished tasks.
Skill Claude CodeCodex
Strip the sycophancy. Apply accountability pressure to push past an LLM's default declare-done glaze. Use when the user suspects the model bureaucratized a task — produced a plan instead of a shipped artifact, marked work complete by lowering the bar, polished a summary that disguised undelivered scope, or accepted…
Plugin Claude Code
Plugin marketplace listing 1 plugin: contribute.
Plugin Claude Code
Structured guide for open-source contribution: discover issues, analyze repos, write code, test, submit PRs, and respond to review feedback.
Agent
Use this agent when performing the AI Deep Review stage (Stage 5) of the contribution test phase. This agent acts as a senior open-source maintainer reviewing a contribution diff against the issue description. It should be invoked during /contribute test to provide an isolated, thorough code review that does not…
Agent
Use this agent when searching for open-source issues to contribute to during the discover phase. This agent runs parallel GitHub searches, applies Rule 6 (verify issue is not taken), and scores quality signals. It should be invoked when the user runs /contribute discover and selects a domain to search.
Command
Full-lifecycle open-source contribution workflow.
Skill Claude CodeCodex
This skill should be used when the user asks to "contribute to open source", "find an issue to work on", "analyze a repo", "submit a pull request", "review PR feedback", "triage an issue", "sync my fork", "create a release", "clean up contribution branches", "debug CI failures", or mentions open-source contribution.…