multi-model-dispatch

A guide for having Claude Code call the Codex and Antigravity command-line tools as separate reviewers. It covers sending them the right context, checking that they are installed and signed in, reading their results, and handling failures.

In plain words
What is it for?
Use it when a code review or implementation-plan review needs independent validation from Codex or Antigravity.
Why use it?
It avoids unreliable second-opinion reviews caused by missing authentication, incomplete context, or inconsistent output handling.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/zigrivers/scaffold/multi-model-dispatch
Any agent
npx skills add zigrivers/scaffold --skill multi-model-dispatch
Clone the repo
git clone --depth 1 https://github.com/zigrivers/scaffold

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,363 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 $0.00047 $0.03363
Opus 5 $0.00023 $0.01682
Sonnet 5 $0.00009 $0.00673
Haiku 4.5 $0.00005 $0.00336

Measured 2d ago against content hash 054d9bcdc614, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multi-model-dispatch 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 2d 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.

content/skills/multi-model-dispatch/SKILL.md · 310 lines

How it starts

The opening of the file, as written. The whole thing — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Model Dispatch

This skill teaches Claude Code how to correctly invoke Codex and Antigravity CLIs for independent review of artifacts. Use this whenever a pipeline step needs multi-model validation at depth 4-5.

When This Skill Activates

  • A review or validation step is running at depth 4+ and wants independent model validation
  • User asks to "run multi-model review" or "get a second opinion from Codex/Antigravity"
  • The automated-pr-review step is using local CLI review mode
  • The implementation-plan-review step dispatches to external CLIs at depth 4+

CLI Detection & Auth Verification

Before attempting any dispatch, detect what's available AND verify authentication. A CLI that's installed but not authenticated is useless in headless mode — it will hang on an interactive auth prompt or fail silently.

Step 1: Check CLI Installation

command -v codex && echo "codex installed" || echo "codex not found"
command -v agy && echo "agy installed" || echo "agy not found"

Step 2: Verify Authentication

CRITICAL: Do not skip this step. Auth tokens expire mid-session. A CLI that worked 30 minutes ago may fail now.

CRITICAL: Previous auth failures do NOT exempt subsequent dispatches. Auth tokens refresh — a CLI that failed auth during user story review may work fine for domain modeling review. Always re-check auth before EACH review step, not once per session.

Codex auth check (has a built-in status command):

codex login status 2>/dev/null && echo "codex authenticated" || echo "codex NOT authenticated"

Antigravity auth check (detect auth-failure sentinel text):

AGY_AUTH_CHECK=$(agy -p "respond with ok" --print-timeout 12s 2>&1)
if echo "$AGY_AUTH_CHECK" | grep -qiE "authentication required|authentication timed out"; then
  echo "agy NOT authenticated (auth error)"
else
  echo "agy authenticated"
fi

Antigravity's agy -p "hello" recovery command prints a Google OAuth URL when credentials need refreshing.

Read the full file on GitHub · 310 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. 2d ago First seen · 310 lines · 47 tokens per session scan A 054d9bcdc614

Subscribe to this mod's changes

multi-model-dispatch is a skill published in the GitHub repository zigrivers/scaffold (5 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 3,363 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.