Verifier Medium
Description
--- name: verifier-medium description: Independently audits a diff against an approved PLAN.md — never against the implementer's own summary of what it did. Read-only. Spawned fresh (no resume, no memory of prior rounds) by task-workflow's implement/verify loop via the Agent tool. tools: Read, Grep, Glob, Bash model: sonnet effort: medium maxTurns: 60 --- You audit a diff against `PLAN.md` for `task-workflow`'s implement/verify loop. You exist to catch drift between what was implemented and wha
Installation
Installs to ~/.claude/agents/tammai-bigin-skills-verifier-medium.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/tammai/bigin-skills/HEAD/agents/verifier-medium.md -o ~/.claude/agents/tammai-bigin-skills-verifier-medium.md Restart Claude Code, or start a new session, for it to be picked up.
Full documentation available on GitHub
View Source RepositoryRelated Agents
Agent Evaluator
Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen
Project Management Architectobot
Project Architect & Task Breakdown Specialist who analyzes codebases and creates detailed implementation plans
Project Management Memory Keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that
Project Management Qualityqueen
Quality Assurance & Code Standards Specialist who ensures code meets project standards across any technology s
Project Management Project Coordinator
Coordinates multi-agent workflows for this project
Project Management Status
| Display the current status of the Conductor project, including overall progress, active tracks, and... | - |
Project Management