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/imagegit 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 | $0.00016 | $0.00357 |
| Opus 5 | $0.00008 | $0.00179 |
| Sonnet 5 | $0.00003 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
image scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
5. If the download fails with a private or reserved network error, retry with `--allow-private-network` for trusted Modellix CDN hosts, or fetch `result.resources[].url` with curl. What it actually says
description: Generate an image with Modellix, or edit one when input images are given. argument-hint: [prompt] [optional image URL or path] disable-model-invocation: true
Generate an image with Modellix. Request: $ARGUMENTS
Follow the Modellix skill (skills/modellix/SKILL.md) for execution policy, credentials, and error handling. This command only fixes the routing.
- If
$ARGUMENTSis empty, ask for a prompt instead of inventing one. - Pick the model:
- A slug named by the user wins; confirm it with
modellix-cli model describe <slug> --jsonif unsure. - Text only →
google/nano-banana-2-lite({"prompt": "..."}). - With input images →
google/nano-banana-2-lite-edit({"prompt": "...", "image": ["<url>"]}).
- A slug named by the user wins; confirm it with
- Submit, wait, and persist:
modellix-cli model run \
--model-slug <slug> \
--body '<json>' \
--wait --timeout 5m --json
modellix-cli task download <task_id> --output-dir ./outputs --json
- One paid submit per invocation. If the outcome is unknown or ambiguous, run
modellix-cli task historyand recover the existing task — never re-run the same submission blindly. - If the download fails with a private or reserved network error, retry with
--allow-private-networkfor trusted Modellix CDN hosts, or fetchresult.resources[].urlwith curl. - Report the model slug, task id, and the local file paths.
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 · 30 lines · 0 tokens per session scan A ac4d20a674d2
image is a command published in the GitHub repository Modellix/modellix-plugin (1 stars, last pushed 20d ago), licensed MIT. It adds 16 tokens to every session and 357 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
frappe-lms
Treat the task as Frappe LMS work.
annotate
Annotate single-cell clusters with CellTypePilot — evidence-based cell-type labeling.
critic
Deep-review a specific cluster with CellTypePilot's Annotation Critic.
ctp-inspect
Inspect single-cell data — auto-detect species, tissue, clusters, embeddings.
sdlc-implement
Standalone issue implementation with Ralph Loop — implements a single Linear issue or free-form spec using fullstack-engineer + self-correcting retry loop.
sdlc
Master orchestrator for the complete 5-phase SDLC pipeline. Runs all phases sequentially with approval gates and handoffs between each phase. Organizes artifacts into handoffs/, docs/, and projects/ directories.