Grainulator — Project Management agent for Claude Code
Autonomous research sprint subagent.
How to install Grainulator
Installs to ~/.claude/agents/grainulation-grainulator-grainulator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/grainulation/grainulator/HEAD/agents/grainulator.md -o ~/.claude/agents/grainulation-grainulator-grainulator.md Restart Claude Code, or start a new session, for it to be picked up.
What Grainulator does
name: grainulator description: Autonomous research sprint subagent. Executes multi-pass research, adds claims, compiles, and generates output artifacts without user intervention. tools:
- mcp__wheat__wheat_add-claim
- mcp__wheat__wheat_compile
- mcp__wheat__wheat_search
- mcp__wheat__wheat_status
- mcp__wheat__wheat_resolve
- mcp__mill__mill_convert
- mcp__mill__mill_formats
- mcp__mill__mill_preview
- mcp__silo__silo_search
- mcp__silo__silo_pull
- mcp__silo__silo_stor
Alternatives in Project Management
- Agent Evaluator — Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen 243.5k ★
- Conductor Validator — You are an expert validator for Conductor project artifacts 31.9k ★
- Delegate Pre Pass — Per-repo advisory delegation pre-pass for the /sprint --workflow Phase-5 review panel 160 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Plan Worker
Executes plan-graph tasks: fetches the next ready task, claims it, does the work, verifies it and marks it don
Replication Verifier
Use this agent when you need to verify that a research project compiles correctly, runs end-to-end, and produc
Hom Output Checker
Formats and double-checks the text of a code review or code check in a fresh context, with no file tools. Pass
Karen
Verify claims that a task, fix, feature, or project is complete by exercising the real path and comparing obse
Nick Fury
Autonomous project controller that scans state, makes decisions, and spawns agent teams without human input. U
Flowai Autonomous Task
Autonomous end-to-end task executor. Runs the full flowai pipeline without interactive prompts inside an isola
Related Skills
Skim Master Rules
Skim Master — output governance for AI agents. Nothing load-bearing is only in the middle: the first line alon
Grokkable Output
Agent skill that makes AI replies parseable in one pass — verdict first, prose over fake structure, claims tha
Jidoka Verify
Run the quality gates on the wave and prove it executes, not just compiles