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.
npx agentmods add commands/grainulation/wheat/prototypegit clone --depth 1 https://github.com/grainulation/wheatWhat 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.
| Model | Per session | Once 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 |
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.
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
-
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.
-
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
-
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_withon both claims - The compiler will auto-resolve in favor of
testedoverweb
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>
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.
- yesterday First seen · 71 lines · 0 tokens per session scan A d7cdc85d6dff
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.
Other commands, from other repositories
advisor
Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.
guide
You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
new
Creates a new item in a module that supports the new capability.
card
Open one self-contained OverClick card.
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.