verify-contract

verify-contract is a skill for Claude Code, Codex from tmusser/ai-engineering-skills. It costs 32 tokens per session (1,330 once invoked), scanned A, original, MIT.

A verification process that records evidence about whether a software task works and stayed within its agreed scope. It documents commands, results, acceptance checks, risks, and any required scope review.

In plain words
What is it for?
Use it after implementations, fixes, data runs, or smoke tests to update VERIFY.md, run available verification and scope checks, and record remaining uncertainty.
Why use it?
It replaces a vague claim that something works with an auditable record. It also catches changes that exceed the task's specification or approved write boundary.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/scope_gate.py --base <frozen-base>.

Good fit Use it after implementations, fixes, data runs, or smoke tests to update VERIFY.md, run available verification and scope checks, and record remaining uncertainty.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/tmusser/ai-engineering-skills
agentmods
npx agentmods add skills/tmusser/ai-engineering-skills/verify-contract

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for verify-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/verify-contract/github.svg)](https://agentmods.dev/skills/tmusser/ai-engineering-skills/verify-contract)
Your own site
<a href="https://agentmods.dev/skills/tmusser/ai-engineering-skills/verify-contract"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/verify-contract/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verify-contract

Your own site · 80×15
<a href="https://agentmods.dev/skills/tmusser/ai-engineering-skills/verify-contract"><img src="https://agentmods.dev/badge/skills/tmusser/ai-engineering-skills/verify-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,330 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00032 $0.01330
Opus 5 $0.00016 $0.00665
Sonnet 5 $0.00006 $0.00266
Haiku 4.5 $0.00003 $0.00133

Measured 9d ago against content hash 9b2a0e9d60ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify-contract 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 9d 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.

skills/verify-contract/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Contract

Purpose

Prove the task actually works and leave durable evidence.

Verification also checks that the implementation did not exceed the behavioral contract or frozen write boundary merely because the extra work looked reasonable.

When to use

After implementation, tests, bug fixes, data runs, or smoke checks.

Inputs

  • Task name
  • SPEC.md acceptance criteria, non-goals, constraints, and invalid-if rules
  • Optional persisted SCOPE.md plus its frozen Git base
  • Commands run or to run
  • Changed files
  • Evidence to record
  • Known risks or untested areas

Workflow

  1. Update VERIFY.md with date + task name.

  2. Record commands run as short evidence entries with command, exit code, relevant output, interpretation, acceptance criterion covered, and remaining uncertainty. Keep each entry concise and auditable.

  3. When SCOPE.md and scripts/scope_gate.py are available, run:

    python scripts/scope_gate.py --base <frozen-base>
    

    Record its status and relevant violations or review triggers. A scope-gate FAIL prevents PASS. REVIEW_REQUIRED also prevents PASS until the named review is resolved.

  4. If scripts/verify_gate.py is available, run it before marking verification complete. If repeated iterations were used, check for a loop contract, budget, ledger, revert rule, and stop condition before calling the work done.

  5. List changed files.

  6. Run the spec ceiling check against the implemented behavior and diff.

  7. Note working directory / environment assumptions if relevant.

  8. Link artifacts/screenshots if relevant (supporting evidence only; automated checks preferred).

  9. Note what was not tested and remaining risks.

  10. Name the next safest task.

Verify gate

Status: PASS | FAIL | REVIEW_REQUIRED

  • PASS only when contract probes pass, the scope gate passes when a persisted scope exists, no diff guard requires review, and no spec ceiling violation is present.
  • FAIL when behavior or contract probes fail, the scope gate fails, or an explicit non-goal / invalid-if rule was violated.
  • REVIEW_REQUIRED when behavior passes but evidence integrity is questionable, the scope gate requires review, or plausible extra behavior exceeds the written acceptance criteria and intent is ambiguous.
  • REVIEW_REQUIRED is not the same as functional failure.
  • If repeated iterations occurred without a loop contract, use REVIEW_REQUIRED.
  • If loop budget, ledger, revert rule, or stop condition was violated, use REVIEW_REQUIRED or FAIL depending on whether the behavior contract failed.
  • Do not treat loop activity as success merely because the final output looks plausible.

Read the full file on GitHub · 169 lines

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. 9d ago First seen · 169 lines · 32 tokens per session scan A 9b2a0e9d60ff

Subscribe to this mod's changes

verify-contract is a skill published in the GitHub repository tmusser/ai-engineering-skills (4 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,330 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.