prototype

A command for building a small, testable proof of concept from a research question and existing findings. It also creates a self-contained web page that demonstrates the result.

In plain words
What is it for?
Use it to create a minimal prototype, provide instructions for running it, make a demo page for non-technical readers, and record findings as tested research claims.
Why use it?
It turns an argument or hypothesis into something runnable and measurable, so the team can learn from an actual test.

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/prototype
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 551 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 $0.00551
Opus 5 $0.00000 $0.00275
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured yesterday against content hash d7cdc85d6dff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prototype 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/prototype.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prototype — Build something testable

You are building a proof-of-concept for the current Wheat sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.

Process

  1. Determine what to prototype: Based on the user's argument and existing research claims. If no argument given, look at the research and suggest the most promising option to test.

  2. Build it: Create a working prototype in prototypes/<name>/. This should be:

    • Minimal — just enough to test the hypothesis
    • Runnable — include a README or run script
    • Measurable — produce output that can be evaluated
  3. Also generate a demo artifact: Create prototypes/<name>/demo.html — a self-contained HTML page that shows what the prototype does, with screenshots, code snippets, or interactive elements. Non-technical stakeholders should be able to understand the prototype from this page alone.

Claim updates

Every prototype finding becomes a claim with evidence tier tested:

{
  "id": "p001",
  "type": "factual",
  "topic": "<what was tested>",
  "content": "<what we found — be specific with numbers>",
  "source": {
    "origin": "prototype",
    "artifact": "prototypes/<name>/",
    "connector": null
  },
  "evidence": "tested",
  "status": "active",
  "phase_added": "prototype",
  "timestamp": "<ISO timestamp>",
  "conflicts_with": [],
  "resolved_by": null,
  "tags": []
}

Critical: Check if any existing research claims (evidence: "web") are contradicted by prototype results. If so:

  • Set conflicts_with on both claims
  • The compiler will auto-resolve in favor of tested over web

Update meta.phase to "prototype" in claims.json if this is the first prototype.

Run the compiler

npx @grainulation/wheat compile --summary

Report evidence upgrades (research claims superseded by prototype findings).

Git commit

Stage claims.json and all new/changed files.

Commit: wheat: /prototype "<name>" — added <claim IDs>

Read the full file on GitHub · 71 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 · 71 lines · 0 tokens per session scan A d7cdc85d6dff

Subscribe to this mod's changes

prototype 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 551 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.