cckyros/goal-acceptance

README excerpt

goal-acceptance English 中文 Acceptance-criteria-driven goal completion for autonomous AI agents. Prevents agents from prematurely declaring "done" by locking immutable acceptance criteria before work begins, tracking validation status with evidence, linking criteria to task progress, respecting dependency ordering, and enforcing completion checks. Advantages 1. Cross-platform compatibility goal-acceptance works with any AI agent platform that supports MCP or Agent Plugins. One package, multiple runtimes: Platform How it connects Turn-stopping enforcement Claude Code MCP stdio server Model voluntarily calls tools Cursor MCP stdio server Model voluntarily calls tools Devin MCP stdio server Model voluntarily calls tools OpenClaw Native plugin ( @cckyros/goal-acceptance-openclaw ) or Agent Plugin bundle Model voluntarily calls tools DeepSeek Harness Cordis plugin ( @cckyros/dsh-goal-acceptance ) Yes — agent.steer() forces continuation Any MCP client stdio MCP server Model voluntarily calls tools Any Agent Plugins client plugin.json + mcp.json + skills Model voluntarily calls tools Any JS/TS runtime Core library ( @cckyros/goal-acceptance-core ) Programmatic —you control it The core stat…

Category