pinocchio
claudeYour agent's nose grows when it lies. Checks "done", "fixed" and "tests pass" claims against the session's test runs, exit codes and git, and blocks the stop only when it has proof. Read-only, offline, ~93 tokens.
3 skills · hooks
Plugin marketplace
Personal Claude Code marketplace by STiFLeR7 — pinocchio (catches false "tests pass" claims), memex (trusted engineering context via temporal knowledge graph) and prompt-forge (multi-perspective prompt refinement).
Add this marketplace
Then install any plugin below by name — each page has its exact command.
Your agent's nose grows when it lies. Checks "done", "fixed" and "tests pass" claims against the session's test runs, exit codes and git, and blocks the stop only when it has proof. Read-only, offline, ~93 tokens.
3 skills · hooks
Advanced prompt refinement skill — extracts your real intent, investigates your codebase, and applies 9 perspective lenses (Security, QA, UX, Performance, …) before producing a grounded prompt for your execution tool.
1 skill · hooks
Trusted engineering context for AI coding agents. Keeps Claude Code and Codex sessions current as the code changes, with checks before edits and scoped corrections.
1 MCP server
Shows how many plugins this repo ships, and links here.