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/modellix/modellix-plugin/modelsgit clone --depth 1 https://github.com/Modellix/modellix-pluginWhat 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 | $0.00014 | $0.00362 |
| Opus 5 | $0.00007 | $0.00181 |
| Sonnet 5 | $0.00003 | $0.00072 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
models 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 yesterday.
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.
What it actually says
Find a Modellix model. Query: $ARGUMENTS
Read-only: never submit a paid task from this command.
- If
$ARGUMENTSlooks like a fullprovider/modelslug, describe it directly:
modellix-cli model describe $ARGUMENTS --json
- Otherwise search the catalog, using the filter that matches the query:
modellix-cli model list --search <term> --limit 20 --json
modellix-cli model list --type text-to-image --output slugs
modellix-cli model list --provider <provider> --limit 20 --json
Common types include text-to-image, image-to-image, text-to-video, image-to-video, video-to-video, text-to-speech, speech-to-text, and speech-to-speech. Treat the live catalog as authoritative.
- For the request-body schema, read the model docs: prefer the Docs MCP when the host has it connected, otherwise the
docs_urlreturned bymodel describe, or the matching entry in https://docs.modellix.ai/llms.txt. - Never invent a slug from a documentation filename — decimals matter (
bytedance/seedance-2.0-mini-t2v, notseedance-2-0-mini-t2v). - Report the candidate slugs, what each is good for, and the required body fields. Then point at
/modellix:image,/modellix:video, or/modellix:audioto run one.
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.
- yesterday First seen · 29 lines · 14 tokens per session scan A 3d249b8a530e
models is a command published in the GitHub repository Modellix/modellix-plugin (1 stars, last pushed 20d ago), licensed MIT. It adds 14 tokens to every session and 362 once invoked, about $0.0001 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.
Other commands, from other repositories
codex-swarm
Swarm a task across parallel Codex (codex exec) sessions with automatic decomposition and model routing.
codex-imagegen
Generate or edit an image via a Codex (codex exec) session — Codex's built-in imagegen tool does what your agent cannot.
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
status
Show 3d-design team status and recent activity.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.