Cad Verifier — Development agent for Claude Code
The high rung of cad-verifier (goal-backward phase verification); bin/route.mjs picks it, not the user.
How to install Cad Verifier
Installs to ~/.claude/agents/crenshawdev-cadence-cad-verifier.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/crenshawdev/cadence/HEAD/agents/cad-verifier.md -o ~/.claude/agents/crenshawdev-cadence-cad-verifier.md Restart Claude Code, or start a new session, for it to be picked up.
What Cad Verifier does
name: cad-verifier description: The `high` rung of `cad-verifier` (goal-backward phase verification); `bin/route.mjs` picks it, not the user. tools: Read, Write, Bash, Grep, Glob color: green effort: high maxTurns: 200 disallowedTools: Edit, MultiEdit skills:
- cad-verifier-contract
Follow the preloaded `cad-verifier-contract` skill exactly - it is your full contract. This file names that contract and adds nothing else.
Alternatives in Development
- Executioner — Optional Sanhedrin fallback verifier 632 ★
- Cold Verifier — Phase 11 cold verification agent that independently re-verifies CRITICAL and HIGH findings with zero prior con 125 ★
- Ac Evidence Verifier — Phase 3.4 evidence verifier 115 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Cad Plan Checker
The low rung of cad-plan-checker (goal-backward plan gate); bin/route.mjs picks it, not the user.
Cad Planner
The high rung of cad-planner (phase plan authoring); bin/route.mjs picks it, not the user.
Dnp Verifier
✅ Goal-backward verification for .NET phases — checks build, tests, DI completeness, migration state, and arch
Engineer High
A phase sub-agent at effort high. Lead picks this type from the phase's effort; the identity, phase and rules
Goal Verifier
Read-only auditor that runs the RoT DTD GOAL verification suite and diagnoses failures without modifying anyth
Odd Verify
Independent ODD verifier. Use only for a high-risk change or when the user asks for verification: checks a fin
Related Skills
Jiahao
Dual-profile prompt-as-mental-model harness for LLM agents — advisory generator profile in the working agent,
Cmd Judge
Adversarial verifier for the PROVE phase: treats a finished-work report as untrusted claims, re-runs every ver
Update Repo
Refresh this repo's staged Genesis binaries to the installed plugin version — restages .genesis/bin so a promo