Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsVerify Gate: no "done" without exit codes
Makes your agent prove the code works: real tests, coverage, lint, types and security scans, each with its exit code, before it may say "done".
Free
About this skill
Stops agents from claiming "all tests pass" without proof. Runs your project's real tests, coverage, linter, type checker, security and secret scans (mirroring your CI first), reports every command with its exit code, and says VERIFY: PASS only when all of them exit 0.
It never installs packages, lowers thresholds or adds ignore rules to get green, and a skipped check makes the verdict INCOMPLETE, not PASS.
Works with Python, TypeScript/JavaScript, Go, Rust, Java/Kotlin and .NET. Part of the agent-forge pipeline (github.com/Ces107/agent-forge).
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean today
- Free to download with an account
Requires
Python
Node.js