---
title: "grainulator"
description: "Evidence and verification for model-assisted work, with portable workflows and clear next actions."
canonical: https://agentpluginsdirectory.com/plugins/grainulator
last-updated: 2026-10-23
---

# grainulator
Evidence and verification for model-assisted work, with portable workflows and clear next actions.
- Slug: grainulator
- Publisher: Grainulation
- Repository: https://github.com/grainulation/grainulator
- Manifest: plugin.json
- Version: 2.0.4
- Category (editorial): other
- Skills: 20 (analytics, blind-spot, brief, calibrate, challenge, feedback, fetch, grainulator, healthcheck, init, orchestrate, present, pull, research, resolve, router, setup, status, sync, witness)
- MCP servers: 1 (grainulator)
- Stars: 86
- Repository created: 2026-03-21
- Repository last pushed: 2026-10-20
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/grainulator
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What grainulator does, in the publisher's words

Grainulator

Evidence and verification for the model you already use.

Keep the evidence. Challenge the answer. Know what to do next. A shared workflow for research, engineering, and model-assisted work.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/grainulation/grainulator/HEAD/README.md

## Skills

- analytics: Sprint analytics: type distributions, stale claims, velocity, prediction scoring
- blind-spot: Structural gap analysis: find what the sprint has not considered.
- brief: Generate a compiled decision brief from the current sprint's claims.
- calibrate: Score past predictions against actual outcomes. Closes the feedback loop.
- challenge: Adversarial testing of a specific claim. Try to disprove it.
- feedback: Record stakeholder input: new constraints, corrections, or direction changes.
- fetch: Size-efficient URL fetch with semantic extraction. Use for ad-hoc web research when you want content without the raw HTML overhead.
- grainulator: Use Grainulator to carry a substantial research or engineering task through investigation, implementation, and evidence-backed verification. Use when the user invokes /grainulator or asks for a tracked Grainulator workflow.
- healthcheck: Check the unified Grainulator MCP server and local CLI without blocking useful work on optional connectors.
- init: Initialize a dedicated sprint using the unified tool or local CLI while preserving existing data.
- orchestrate: Multi-sprint orchestration: view dependency graph, dispatch next ready sprint
- present: Generate a presentation deck from the compiled sprint data.
- pull
- research
- resolve
- router
- setup
- status
- sync
- witness

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- grainulator: transport: stdio; command: node ${PLUGIN_ROOT}/bin/grainulator-plugin.js; env: GRAINULATOR_MEMORY_DIR

Read from the plugin's own mcp.json. Environment variable names only, never values.