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.
npx agentmods add commands/watchandytw/multi-model-team/mmt-setupgit clone --depth 1 https://github.com/WatchAndyTW/multi-model-teamWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00048 | $0.00877 |
| Opus 5 | $0.00024 | $0.00439 |
| Sonnet 5 | $0.00010 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade B, and why
mmt-setup scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` with the absolute path to this plugin's statusline: The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 2d ago First seen · 82 lines · 48 tokens per session scan B 637729c583b4
mmt-setup is a command published in the GitHub repository WatchAndyTW/multi-model-team (5 stars, last pushed 19d ago), with no licence file. It adds 48 tokens to every session and 877 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
media
Understand an audio / video / image file — Antigravity (agy/Gemini) transcribes and analyzes it, returning a timestamped digest while the full transcript goes to a file.
cloud-run-debug
Diagnose a failing Cloud Run service — Antigravity (agy/Gemini) digests the error logs cheaply, Claude infers the root cause and proposes a fix. Read-only by default; --apply writes the fix to a branch.
delegate
Delegate a well-scoped subtask to Antigravity (agy/Gemini) under cost discipline, then verify.
research
Claude-orchestrated deep research — Antigravity (agy/Gemini) does the grounded web legwork; Claude plans, verifies the citations, and synthesizes.
review
Get an independent cross-model review of the current diff from Antigravity (Gemini), then reconcile as the final judge.
result
Fetch the output of a finished background Antigravity (agy) job, then verify it.