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/briefgit 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 | $0.00835 |
| Opus 5 | $0.00000 | $0.00417 |
| Sonnet 5 | $0.00000 | $0.00167 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
brief 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/brief — Compile the decision document
You are compiling the final decision brief for this Wheat sprint. This is the Bran compilation step — deterministic output from resolved claims.
Default behavior: Generate next steps only (fast). The full brief is opt-in via --full.
Process
-
Run the compiler with check:
npx @grainulation/wheat compile --checkIf the compiler returns an error (exit code 1), STOP. Do not generate a brief. Instead:
- Show the user the compilation errors
- Explain what needs to be resolved
- Suggest specific commands to fix each blocker
- Do NOT proceed until compilation passes
-
Always: Generate next steps — Read compilation.json, summarize sprint state (claim counts, conflicts, coverage), and suggest 2-4 concrete next actions. Then run
/nextto route through Farmer. -
If
--fullflag is passed OR user explicitly asks for the brief: Launch brief generation as a background agent so it's non-blocking. The user continues deciding next steps while the brief builds.To launch in background: use the Agent tool with
run_in_background: trueto generate the full brief (steps 4-7 below). Tell the user "Brief generating in background — I'll let you know when it's ready."If no
--fullflag, skip steps 4-7 entirely. -
Read compilation.json — use ONLY
resolved_claimsas your source material. Never read claims.json directly for the brief. -
Generate the brief as markdown: Create
output/brief.mdwith this structure:# Decision Brief: [Sprint Question] **Date**: [date] | **Audience**: [audience] | **Phase**: Compiled ## Executive Summary [2-3 sentences: the recommendation and why] ## Recommendation [The recommended course of action, with specific next steps] ## Evidence Summary [For each topic: key findings, evidence tier, source] [Every statement must cite a claim ID] ## Tradeoffs and Risks [Risks identified, with evidence tier for each] ## Resolved Conflicts [What disagreed, how it was resolved, what evidence won] ## Appendix: Claim Inventory [Table of all resolved claims: ID, type, content, evidence, source] --- Compilation certificate: [hash] | Compiler: wheat v[version] | Claims: [count] | Compiled: [timestamp]
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 · 100 lines · 0 tokens per session scan A d8a840889c7e
brief 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 835 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.