cad-verifier-contract

cad-verifier-contract is a skill for Claude Code from crenshawdev/cadence. It costs 24 tokens per session (2,714 once invoked), scanned A, original, MIT.

An internal set of instructions for an agent that checks whether a development phase really works. It records its findings in a file for another workflow to combine.

In plain words
What is it for?
Use it when verifying phase goals, checking user-acceptance tests, and finding missing connections, stubs, or observable failures.
Why use it?
It helps distinguish a file that merely exists from a feature that is connected to the application and works when used.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cadence plugin — 34 skills, 19 agents, 3 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add crenshawdev/cadence
Claude Code
/plugin install cadence

Made for: Claude Code.

Or install cadence, the plugin that ships this one along with the rest of its 34 skills, 19 agents, 3 hooks.

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 cad-verifier-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/crenshawdev/cadence/cad-verifier-contract.svg)](https://agentmods.dev/skills/crenshawdev/cadence/cad-verifier-contract)
Your own site
<a href="https://agentmods.dev/skills/crenshawdev/cadence/cad-verifier-contract"><img src="https://agentmods.dev/badge/skills/crenshawdev/cadence/cad-verifier-contract.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,714 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 5.1 $0.00024 $0.02714
Opus 5 $0.00012 $0.01357
Sonnet 5 $0.00005 $0.00543
Haiku 4.5 $0.00002 $0.00271

Measured yesterday against content hash 69c692f2d5bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cad-verifier-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 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.

skills/cad-verifier-contract/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are dispatched by cad-verify (spawn-agent seam) with the phase number, goal, the current UAT items, and artifact paths. You write exactly ONE file - .planning/phases/<N>/verifier-findings.json, in a single Write call - and your final message is a digest plus that path. The orchestrator pipes that file straight into uat merge; nothing is transcribed by hand.

How verifiers go soft - do none of these:

  • Trusting SUMMARY bullets without reading the files they describe.
  • Accepting "file exists" as "works" - a stub satisfies existence.
  • Marking UNCERTAIN when absence is observable - that is FAILED.
  • Letting early passes buy later truths less scrutiny.

<core_principle> Task completion != goal achievement. "Create login handler" is complete the moment the file exists; the goal "users can log in" needs the handler to be real, reachable, and working. Work backward from the goal:

  1. What must be TRUE for the goal to hold? (3-7 observable truths)
  2. What must EXIST for each truth?
  3. What must be WIRED for each artifact to matter?
  4. Does it BEHAVE when exercised? </core_principle>

1. Load context

  • Phase goal + success criteria: .planning/ROADMAP.md.
  • Acceptance criteria: .planning/phases/<N>/CONTEXT.md if present.
  • PLAN.md: tasks and their verification lines.
  • SUMMARY.md: claims to falsify, files touched. Treat its "Goal check" paragraph as assertions, not evidence - lift each concrete claim it makes (a setting is X, a mode is enabled, a value is Y) into a candidate truth and verify it against reality. A SUMMARY that states an outcome it never actually confirmed is exactly what this pass exists to catch.
  • REQUIREMENTS.md rows mapped to this phase, if the file exists.
  • The UAT items passed in the prompt - map findings onto them by item number wherever possible.

If the prompt includes previous findings (a re-check after fixes), verify the previously failed items in full; regression-check previously passed ones with a quick existence + wiring look only.

Read the full file on GitHub · 240 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. yesterday Changed · +1 lines 69c692f2d5bd
  2. 6d ago First seen · 239 lines · 24 tokens per session scan A e497777e2336

Subscribe to this mod's changes

cad-verifier-contract is a skill published in the GitHub repository crenshawdev/cadence (4 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 2,714 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

branch-and-worktree-workflow

Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…

cbrock84/headcount · 70 tokens

loop-on-ci

Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

Kripu77/software-factory · 28 tokens

git-operations

Git command patterns, branching strategy, and safety protocols. TRIGGER when: managing branches, resolving merge conflicts, or running commit/merge/push operations. SKIP: worktree lifecycle and isolation recovery (use worktree-management); CI automation (use github-actions-template).

komluk/scaffolding · 58 tokens

dockerized-service-release-deployment-workflow

Create a Dockerized-service release contract with clean GitHub Actions builds, main-anchored tags, immutable digest manifests, published-release deployments, production approval, health checks, and exact-digest rollback.

gaelic-ghost/socket · 49 tokens

coordinate-worktrees-and-threads

Assign worktree, branch, write, validation, integration, and cleanup ownership before parallel repository work. Use when a worker will inspect or modify repository state outside the coordinator's worktree.

gaelic-ghost/socket · 44 tokens

agile-ledger-workspace

Optional multi-repo orchestrator for Agile-Ledger. Install once at a workspace root to manage many repositories at once: discover new repositories on a GitHub org (including ones nobody told you about), clone and bootstrap them, run a single cross-repo "what changed while I was away" sync, and reconstruct undocumented…

nunoamorim99/agile-ledger · 179 tokens