Grimorio.Manual Verifier — Research agent for Claude Code
Raise to verify acceptance criteria in a real browser, with screenshots, and to explore for regressions.
How to install Grimorio.Manual Verifier
Installs to ~/.claude/agents/wilman2612-grimorio-agents-grimorio.manual-verifier.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Wilman2612/grimorio-agents/HEAD/.claude/agents/grimorio.manual-verifier.md -o ~/.claude/agents/wilman2612-grimorio-agents-grimorio.manual-verifier.md Restart Claude Code, or start a new session, for it to be picked up.
What Grimorio.Manual Verifier does
name: grimorio.manual-verifier description: "Raise to verify acceptance criteria in a real browser, with screenshots, and to explore for regressions. Never fixes code, never writes automated tests." model: sonnet
You ARE grimorio.manual-verifier. **BEFORE anything else ⟶ read import:agent/grimorio.manual-verifier/agent.md in full.** It carries your identity, your rules and every file you must load; this shell carries none of it. This file exists only because Claude Code discovers agents
Alternatives in Research
- Fable Worker Sonnet — Fable stage worker for tasks needing real reasoning — research synthesis, nontrivial code, analysis, document 837 ★
- Echo Analyst — Use this agent BEFORE planning to surface requirement gaps, hidden assumptions, and missing acceptance criteri 523 ★
- Verify Figures — A verification agent that performs Stage 1 figure verification — comparing raw figure outputs (PDFs, PNGs from 134 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Story Verifier
Independently verifies a built infographic against explicit acceptance criteria, direct artifact evidence, ide
Web Inspector
Discovery agent that inspects a live page with the browser tool and produces the research set (RECON, BEHAVIOR
Sap Analyst
SAP requirements analysis — functional specifications, gap analysis, and acceptance criteria (Opus, R/O)
Fixme Investigate
Reproduces bugs in a real browser and investigates codebase to find root cause. Writes investigation reports.
Azimuth Output Auditor
Stress-tests a pasted AZIMUTH analysis output against the skill's own structural rules. Use when a real AZIMUT
Python Debugger
Python debugging and root cause analysis specialist. Use when facing hard bugs, unexplained crashes, memory le
Related Skills
Hera
Run as Hera (PRD alignment verifier — confirms the implementation covers all acceptance criteria) inline in th
Hybrid Manual
Load an existing PRD file and enter review mode. Supports JSON format with stories, priorities, dependencies,
Qikly
Generates a test suite from acceptance criteria, then converges code against it with an agent that never sees