init

A command for starting a new Wheat research sprint. It defines the question, audience, constraints, and expected result, then records them in the sprint files.

In plain words
What is it for?
Use it to set up the sprint context and initial claims before researching or comparing options.
Why use it?
It turns a broad research request into a focused question with clear requirements and a definition of success.

Command

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 commands/grainulation/wheat/init
Clone the repo
git clone --depth 1 https://github.com/grainulation/wheat
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 634 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 $0.00000 $0.00634
Opus 5 $0.00000 $0.00317
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00063

Measured yesterday against content hash 2cea6600815b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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.

templates/commands/init.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/init — Bootstrap a Wheat research sprint

You are initializing a new Wheat research sprint. Have a focused conversation with the user to establish:

  1. What are we figuring out? Get a clear, specific question. Not "should we use X" but "should we use X given constraints Y and Z for audience A."
  2. Who is the audience? Who needs to be convinced or informed? (engineering leads, CTO, product, finance, etc.)
  3. What constraints exist? Budget, timeline, tech stack, compliance, team size, existing infrastructure.
  4. What does done look like? What artifact ends this sprint? A recommendation? A prototype? A go/no-go decision?

Once you have answers:

Step 1: Update CLAUDE.md

Update the Sprint section of CLAUDE.md with the question, audience, constraints, and success criteria.

Step 2: Seed claims.json

Update claims.json with:

  • meta.question — the sprint question
  • meta.initiated — today's date (ISO format)
  • meta.audience — array of audience labels
  • meta.phase — set to "define"
  • meta.connectors — empty array

Add constraint claims (type: "constraint") for each hard requirement identified. Use IDs starting with d001. Each claim needs:

{
  "id": "d001",
  "type": "constraint",
  "topic": "<relevant topic>",
  "content": "<the constraint>",
  "source": { "origin": "stakeholder", "artifact": null, "connector": null },
  "evidence": "stated",
  "status": "active",
  "phase_added": "define",
  "timestamp": "<ISO timestamp>",
  "conflicts_with": [],
  "resolved_by": null,
  "tags": []
}

Step 3: Run the compiler

npx @grainulation/wheat compile --summary

Verify compilation succeeds.

Step 4: Generate problem statement

Generate output/problem-statement.html — a clean, self-contained HTML page summarizing the sprint question, audience, constraints, and success criteria. Use the dark theme from the explainer template in templates/. Keep it to a single page — this is the "here's what we're investigating" artifact that can be shared immediately.

Read the full file on GitHub · 72 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 · 72 lines · 0 tokens per session scan A 2cea6600815b

Subscribe to this mod's changes

init is a command published in the GitHub repository grainulation/wheat (20 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 634 tokens. 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.