synaptiai/agent-capability-standard

4 stars · Last commit 2026-04-01

Agent Capability Standard is an open specification for composable AI agent capabilities. It defines 36 atomic capabilities across 9 cognitive layers, a type-safe workflow DSL, and grounded world modeling with trust-aware conflict resolution. Built on the Grounded Agency philosophy, it makes agent reliability structural—not optional.

PluginWorkflow & Automation TDD & Testing Debugging Documentation Design & UI DevOps & Infra Productivity AI & Prompting Data & ML Security

README preview

# Agent Capability Standard

> **Grounded Agency**: A framework for building AI agents that know what they don't know.

[![Claude Code Plugin](https://img.shields.io/badge/Claude_Code-Plugin-blueviolet?logo=anthropic)](https://github.com/synaptiai/synapti-marketplace)
[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
[![Spec](https://img.shields.io/badge/Spec-v1.0.0-blue.svg)](spec/STANDARD-v1.0.0.md)
[![Plugin](https://img.shields.io/badge/Plugin-v1.2.0-green.svg)](CHANGELOG.md)

> **Versioning:** The spec version (v1.0.0) tracks the standard itself. The plugin version (v1.2.0) tracks the Claude Code implementation. The Python package (`grounded-agency`) uses its own SemVer. See [GOVERNANCE.md](spec/GOVERNANCE.md) for the versioning policy.

```bash
# Install as Claude Code plugin
claude plugin marketplace add synaptiai/synapti-marketplace
claude plugin install agent-capability-standard
```

---

## What Is This?

View full repository on GitHub →