setup

A setup guide for Grainulator, a local research workflow that stores claims, converts documents, and manages research sprints. MCP servers are local helper programs that let the agent use these functions.

In plain words
What is it for?
Use it after installation, when a server fails, or when you need to check the research, document-conversion, and sprint setup and start a first sprint.
Why use it?
It helps identify why Grainulator's helper programs are not connecting and handles optional dependencies before work begins.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/grainulation/grainulator/setup
Any agent
npx skills add grainulation/grainulator --skill setup
Clone the repo
git clone --depth 1 https://github.com/grainulation/grainulator

Made for: Claude Code, Codex.

Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,416 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00061 $0.01416
Opus 5 $0.00030 $0.00708
Sonnet 5 $0.00012 $0.00283
Haiku 4.5 $0.00006 $0.00142

Measured yesterday against content hash 3da530375ad8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/setup/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/setup -- Configure and verify Grainulator

The user wants to set up Grainulator or verify that all MCP servers and dependencies are working correctly.

Arguments

$ARGUMENTS

Instructions

Phase 1: Verify core MCP servers

Grainulator bundles three core MCP servers that run locally via npx. Check each one in order:

  1. Wheat (research claims engine)

    • Purpose: Manages typed claims (claims.json), compiles sprint state, resolves conflicts, and searches across claims. This is the backbone of every research sprint.
    • Verify: Call wheat_status. If it returns sprint data or a "no sprint found" message, the server is healthy.
    • If it fails: The @grainulation/wheat npm package may not be accessible. Ask the user to run npx -y @grainulation/wheat manually to check for npm/network issues.
    • Sprint data (claims.json, compilation.json) lives in the project root.
  2. Mill (format conversion engine)

    • Purpose: Converts between document formats (Markdown, HTML, PDF). Used by /brief and /present to produce output artifacts.
    • Verify: Call mill_formats. If it returns a list of supported formats, the server is healthy.
    • If it fails: The @grainulation/mill npm package may not be accessible. Same troubleshooting as Wheat.
  3. Silo (knowledge storage)

    • Purpose: Stores and retrieves knowledge packs, manages a graph of connected concepts, and integrates with Confluence. Used by /research and /pull for knowledge reuse across sprints.
    • Verify: Call silo_list. If it returns a list (even empty), the server is healthy.
    • If it fails: The @grainulation/silo npm package may not be accessible. Note that Silo uses ${CLAUDE_PLUGIN_DATA}/silo for persistent storage.

Report the status of each server:

MCP Server Status:
  wheat  ✓ running  (claims engine)
  mill   ✓ running  (format conversion)
  silo   ✓ running  (knowledge storage)

If any server fails, show the error and suggest a fix. Do NOT proceed to Phase 2 until all three core servers are confirmed running.

Read the full file on GitHub · 132 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 132 lines · 61 tokens per session scan A 3da530375ad8

Subscribe to this mod's changes

setup is a skill published in the GitHub repository grainulation/grainulator (87 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 1,416 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.