ZhangHanDong/agent-spec

`agent-spec` is an AI-native BDD/spec verification tool for task execution.

46
/ 100
Emerging

This tool helps software development teams precisely define and verify that an AI agent or developer has correctly implemented a task. You provide a "Task Contract" outlining what needs to be done, technical choices, allowed changes, and specific pass/fail scenarios. The tool then checks if the implemented code meets these requirements, ensuring everyone agrees on the expected behavior.

Use this if you need a clear, verifiable way to ensure that software tasks, especially those implemented by AI agents or developers, meet precise requirements and behave as expected.

Not ideal if your project lacks formal specification needs or if you prefer less structured, more agile development without explicit contract-based verification.

Software Development Requirements Management Quality Assurance AI Agent Management Behavior-Driven Development
No Package No Dependents
Maintenance 10 / 25
Adoption 13 / 25
Maturity 11 / 25
Community 12 / 25

How are scores calculated?

Stars

77

Forks

8

Language

Rust

License

MIT

Last pushed

Mar 11, 2026

Monthly downloads

51

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/ZhangHanDong/agent-spec"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.