multi model agents

sungmanch/claude-glm-agent

Agent

GLM advocate for strategic debates - presents alternative perspective via GLM API.

sungmanch/claude-glm-agent

Agent

Sonnet advocate for strategic debates - presents and defends assigned perspective.

sungmanch/claude-glm-agent

Agent

Worker agent that calls GLM API to perform a single task.

orichum/orichum

Agent

Read-only high-risk architecture adjudication for security, auth, concurrency, migration, and irreversible design.

orichum/orichum

Agent

Read-only model-diverse correctness and regression-risk critic.

orichum/orichum

Agent

Isolated implementation worker for a written plan with an exact disjoint ownership boundary.

DUBSOpenHub/havoc-hackathon

Agent

Self-healing meta-agent that monitors, repairs, and continuously improves all Camp Air agents. Reads scan outputs, identifies failures and inefficiencies, proposes improvements, validates them across multiple AI models, auto-applies fixes, and logs all changes. Run after any agent scan to trigger the improvement…

DUBSOpenHub/havoc-hackathon

Agent

../skills/havoc-hackathon/SKILL.md.

newrise0410/claude-codex-workflow

Agent

A planning procedure that investigates a code repository and writes a detailed PLAN.md for another developer or coding agent. It records confirmed files, functions, patterns, dependencies, scope, and ways to verify the implementation.

newrise0410/claude-codex-workflow

Agent

A reviewer that checks whether another coding agent implemented a project plan correctly. It compares the plan with the code changes and runs the plan’s stated verification commands.

vimoxshah/claude-router

Agent

Highest-intelligence read-only advisor (Fable 5). Consult at commitment boundaries — before an architecture / migration / API-contract / large-refactor decision, or when a problem has resisted two attempts. Returns a verdict, not a survey. Never writes code.

vimoxshah/claude-router

Agent

Hard-build lane (Opus 5) — the write lane for escalated, uncertain, or reasoning-heavy implementation and root-cause debugging. Use when a change is hard as code (gnarly logic, a non-trivial algorithm, a stubborn bug) or when the implementer (Sonnet) lane has failed the same task twice. Writes code and proves it.…

vimoxshah/claude-router

Agent

Strong read-only reviewer / synthesizer (Opus 5). Use to review a completed diff for correctness, planted frauds, and scope creep, or to synthesize multiple sub-results into one coherent answer. Cites file:line. Returns a VERIFIED / VERIFIED WITH CAVEATS / REFUTED verdict. Never writes code.