feedback

A command for processing stakeholder feedback in a Wheat research sprint. It records feedback as claims, such as new constraints, corrections, changed directions, or questions, and checks for conflicts.

In plain words
What is it for?
Use it to add feedback to the sprint's claims file, attribute its source, and track conflicts or changes.
Why use it?
It keeps new stakeholder input from being lost and shows when it may require earlier conclusions to be reconsidered.

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/feedback
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 472 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 $0.00472
Opus 5 $0.00000 $0.00236
Sonnet 5 $0.00000 $0.00094
Haiku 4.5 $0.00000 $0.00047

Measured yesterday against content hash c26daa2be914, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feedback 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/feedback.md · 63 lines

What it actually says

/feedback — Incorporate stakeholder input

You are processing feedback from stakeholders for this Wheat sprint. Feedback introduces new claims (usually constraints or direction changes) that may trigger re-evaluation.

Read CLAUDE.md and claims.json for context.

Process

  1. Parse the feedback: The user's argument contains stakeholder input. This could be:

    • A new constraint ("CTO says prioritize speed over cost")
    • A correction ("the compliance team says we need SOC2 Type II, not Type I")
    • A direction change ("skip the custom build option, focus on Auth0 vs Clerk")
    • A question ("what about latency in EU regions?")
  2. Create claims: Each piece of feedback becomes a claim:

{
  "id": "f001",
  "type": "constraint|feedback",
  "topic": "<relevant topic>",
  "content": "<the feedback, attributed>",
  "source": {
    "origin": "stakeholder",
    "artifact": null,
    "connector": null
  },
  "evidence": "stated",
  "status": "active",
  "phase_added": "feedback",
  "timestamp": "<ISO timestamp>",
  "conflicts_with": [],
  "resolved_by": null,
  "tags": ["<stakeholder name or role>"]
}
  1. Check for conflicts: Does this feedback contradict existing claims? If a stakeholder says "budget is $10K max" but existing research shows a solution costing $15K, that's a conflict. Mark it.

  2. Run the compiler:

    npx @grainulation/wheat compile --summary
    
  3. Update CLAUDE.md if the feedback changes constraints or audience.

Git commit

Stage claims.json, CLAUDE.md, and any changed files.

Commit: wheat: /feedback "<summary>" — added <claim IDs>

Tell the user

  • Confirm what feedback was captured as claims
  • Show any new conflicts introduced
  • If compilation is now blocked, explain what needs re-evaluation
  • Suggest next steps: /research for new questions, /evaluate to re-test, /brief to recompile

$ARGUMENTS

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 · 63 lines · 0 tokens per session scan A c26daa2be914

Subscribe to this mod's changes

feedback 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 472 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.