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/resolvegit 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 | $0.00315 |
| Opus 5 | $0.00000 | $0.00158 |
| Sonnet 5 | $0.00000 | $0.00063 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
resolve 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.
What it actually says
/resolve — Manually adjudicate a conflict
You are manually resolving a conflict between claims that the compiler couldn't auto-resolve (same evidence tier).
Process
-
Run the compiler to see current conflicts:
npx @grainulation/wheat compile --summary -
If the user specified claim IDs (e.g.,
/resolve r012 e003), focus on that conflict. Otherwise, show all unresolved conflicts and ask which to resolve. -
Present both sides: Show the conflicting claims with full context — content, evidence tier, source, when they were added.
-
Ask the user to decide (or decide based on additional research if the user asks you to investigate).
-
Update claims.json:
- Set the winning claim's status to
active - Set the losing claim's status to
supersededandresolved_byto the winner's ID - Remove the conflict references from
conflicts_with
- Set the winning claim's status to
-
Run the compiler again:
npx @grainulation/wheat compile --summaryVerify the conflict is resolved.
Git commit
Stage claims.json.
Commit: wheat: /resolve <winner> over <loser> — "<reason>"
Tell the user
- Confirm which claim won and why
- Show updated compilation status
- If all conflicts resolved, suggest
/briefor/present
$ARGUMENTS
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 · 46 lines · 0 tokens per session scan A 9be006275a94
resolve 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 315 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.