Acceptance-criteria-driven goal completion for autonomous agents — core library, MCP server, and Cordis plugin
Skill Claude CodeCodex
Acceptance-criteria-driven goal completion for the {{brand}} plugin — lock criteria before implementing, track task status, validate with real evidence, and confirm by an independent reviewer. Trigger words: {{name}}, acceptance criteria, goal acceptance, goal planning.
Skill Claude CodeCodex
Append new acceptance criteria after the initial lock.
Skill Claude CodeCodex
Check whether the goal can be completed based on current acceptance criteria. Blocks on self-claimed required criteria.
Skill Claude CodeCodex
Independent reviewer confirms a self-claimed passed criterion with fresh evidence. Must be called by a different agent than the one that did the work.
Skill Claude CodeCodex
Read the current acceptance criteria and their evaluation summary.
Skill Claude CodeCodex
Spawn a planning subagent to decompose a task into non-overlapping, fully-covering acceptance criteria before any implementation work begins.
Skill Claude CodeCodex
Set and lock the acceptance criteria before starting autonomous work. For multi-step tasks, use the goal-planning skill first to spawn a planning subagent.
Skill Claude CodeCodex
Update the status of a task linked to one or more acceptance criteria.
Skill Claude CodeCodex
Record status and evidence for one acceptance criterion. Evidence must come from actual execution, not from memory or assumption.
Skill Claude CodeCodex
Acceptance-criteria-driven goal completion for the goal-acceptance plugin — lock criteria before implementing, track task status, validate with real evidence, and confirm by an independent reviewer. Trigger words: @cckyros/goal-acceptance, acceptance criteria, goal acceptance, goal planning.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: