Cad Verifier Max — Development agent for Claude Code
The max rung of cad-verifier; bin/route.mjs picks it, not the user.
How to install Cad Verifier Max
Installs to ~/.claude/agents/crenshawdev-cadence-cad-verifier-max.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/crenshawdev/cadence/HEAD/agents/cad-verifier-max.md -o ~/.claude/agents/crenshawdev-cadence-cad-verifier-max.md Restart Claude Code, or start a new session, for it to be picked up.
What Cad Verifier Max does
name: cad-verifier-max description: The `max` rung of `cad-verifier`; `bin/route.mjs` picks it, not the user. tools: Read, Write, Bash, Grep, Glob color: green effort: max 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
- Re Lead — PHẢI dùng khi cần reverse-engineer 1 model/tính năng MỚI từ binary đã compile (.so/.apk/.dll/.bin) mà kiến trú 90 ★
- Codex Cross Reviewer — Cross-review orchestrator using Codex CLI as 2nd reviewer 50 ★
- Miner Max — Delegate worker pinned to MAX reasoning effort, the most expensive tier and session-only 31 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Cad Planner Max
The max rung of cad-planner; bin/route.mjs picks it, not the user.
Cad Reviewer Max
The max rung of cad-reviewer; bin/route.mjs picks it, not the user.
Engineer Max
A phase sub-agent at effort max. Lead picks this type from the phase's effort; the identity, phase and rules a
Pedagogy Critic
Independent mastery verifier. Re-reads the vault with fresh context, runs lesson-gate.mjs, and is the ONLY rol
Engagement Critic
Independent reward verifier. Re-reads the vault with fresh context, runs engagement-gate.mjs, and is the ONLY
Architecture Gap Scout
Runs find-architecture-gaps over a given scope, dedupes against previously reported initiatives, and files new
Related Skills
Jiahao
Dual-profile prompt-as-mental-model harness for LLM agents — advisory generator profile in the working agent,
Update Repo
Refresh this repo's staged Genesis binaries to the installed plugin version — restages .genesis/bin so a promo
Mad Max
Unattended backlog-drain mode — runs executor → verifier → code-reviewer loops on all ready tasks, logs stuck/