Skip to content

Contracts, Preflight, and Evidence

A prompt that worked once is an anecdote. A tool with contracts, deterministic preflight, and saved evidence is something you can maintain. CmdForge separates structural proof from semantic judgment so the score never promises more than the tests demonstrate.

Declare the Boundary

input_schema:
  type: object
  properties:
    input: {type: string, minLength: 1}
    limit: {type: integer, minimum: 1, maximum: 20}
  required: [input]

output_schema:
  type: object
  properties:
    topics:
      type: array
      items: {type: string}
      maxItems: 20
  required: [topics]
  additionalProperties: false

Contracts describe shape, not truth. CmdForge can prove that topics is an array of at most twenty strings; it cannot prove those topics are insightful without behavioral evidence.

Read the Preflight Report

cmdforge inspect topic-extractor
cmdforge inspect topic-extractor --registry

Preflight checks configuration integrity, JSON Schema validity, secret-like values, dependencies, ToolStep compatibility, deterministic conformance, reuse opportunities, and—when requested—similar registry tools. It does not call a real AI provider.

Save a Regression Baseline

cmdforge inspect topic-extractor --save-baseline

A baseline records passing deterministic evidence. On the next inspection, CmdForge compares states and contracts. A changed contract is visible; a newly failing case is a regression.

Compose with Eyes Open

When a ToolStep feeds one contracted tool into another, CmdForge performs conservative producer-to-consumer schema analysis. Compatible means the declared output is safe for the declared input. Unknown remains unknown rather than being upgraded to “probably fine.”

Understand the Quality Score

The 0–100 score is a summary with an evidence-coverage percentage, not a popularity contest:

SignalWhat it can support
ContractsDeclared and valid input/output boundaries
Deterministic testsRepeatable structural behavior without paid AI
Regression historyComparison with an accepted baseline
Security scrutinyTransparent behavior and suspicious-pattern checks
Community evidenceReviews and observed ecosystem experience

Read score and coverage together

A score of 100 at 35% coverage means every measured signal passed; it does not mean every possible property was measured.

The Two-Stage Publish Habit

cmdforge registry publish ./.cmdforge/topic-extractor --dry-run
cmdforge registry publish ./.cmdforge/topic-extractor

The dry run executes local and registry preflight but creates no release. Published versions are immutable, so fix warnings and bump deliberately before the second command.