By AmirShayegh
Run the probe loop to verify whether software actually works against the real runtime. Catches silent no-ops, environment mismatches, swallowed errors, hardcoded parameters, cross-layer trust violations, and destructive edge cases.
A Claude Code plugin marketplace for verifying software against the real runtime, not just against its own contracts.
Tests verify contracts. Probes verify reality.
Add the marketplace:
/plugin marketplace add amirshayegh/probe-loop
Install the plugin:
/plugin install probe-loop@probe-loop
Then reload:
/reload-plugins
The probe loop is a five-stage verification pass that catches bugs surviving green test suites:
It catches six categories of bug:
The skill activates on prompts like:
The probe loop is a verification practice that became affordable when agents could hold the codebase, the failure trace, and the regression-test draft inside a single context. The full rationale is at shayegh.ca/blog.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub amirshayegh/probe-loop --plugin probe-loopComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Design fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.