calibrate

A command that checks whether predictions made during a software sprint matched what actually happened after implementation. A sprint is a short, planned period of development work.

In plain words
What is it for?
Use it after work is implemented to compare predicted and actual outcomes, record calibration claims, update calibration data, and print an accuracy scorecard.
Why use it?
It closes the gap between estimates and real results, such as delivery time or yearly cost. The resulting scorecard shows which kinds of predictions are more reliable.

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/calibrate
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 327 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 $0.00327
Opus 5 $0.00000 $0.00163
Sonnet 5 $0.00000 $0.00065
Haiku 4.5 $0.00000 $0.00033

Measured 2d ago against content hash 217c0f169aeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

calibrate 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 2d ago.

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/calibrate.md · 42 lines

What it actually says

/calibrate — Score Past Predictions Against Reality

You are checking what actually happened after a sprint's recommendations were implemented. This closes the feedback loop by comparing predictions to outcomes.

Process

  1. Parse the outcome: The user provides outcome data, either as:

    • Free text: /calibrate --outcome "Shipped Auth0. Took 3 weeks not 2. Costs $18K/year not $15K."
    • Claim-specific: /calibrate e003 "actual: 3 weeks, $18K/year"
  2. Read the sprint data and match outcomes to original predictions.

  3. Create calibration claims (cal### prefix, evidence: production).

  4. Compute accuracy scorecard by evidence tier, source origin, and claim type.

  5. Write/update calibration.json and add claims to claims.json:

    npx @grainulation/wheat compile --summary
    
  6. Print the scorecard to the terminal.

The meta-insight

This is the only command that validates the framework itself. If tested claims are right 95% of the time and web 65%, the tier system works.

Git commit

Commit: wheat: /calibrate — scored <N> predictions against outcomes

Tell the user

  • The accuracy scorecard
  • Which predictions were wrong and by how much
  • Whether the evidence tier hierarchy is predictive
  • Suggest: future sprints should weight evidence tiers based on this data

$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. 2d ago First seen · 42 lines · 0 tokens per session scan A 217c0f169aeb

Subscribe to this mod's changes

calibrate 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 327 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.