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/tasksgit 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 | $0.00015 | $0.00303 |
| Opus 5 | $0.00008 | $0.00151 |
| Sonnet 5 | $0.00003 | $0.00061 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
tasks 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
Inspect Modellix tasks. Target: $ARGUMENTS
Read-only: never submit a new paid task from this command — recovery means finding the task that already exists.
- Without a task id, list what this machine recorded:
modellix-cli task history --limit 20 --json
History stores task id, profile, API origin, model slug, status, and timestamps — never keys or request bodies.
- With a task id, read its current state:
modellix-cli task get $ARGUMENTS --json
- If it is still running, wait instead of resubmitting:
modellix-cli task wait $ARGUMENTS --interval 5s --timeout 10m --json
Exit code 124 means the local wait timed out, not that the task failed; wait again or check back later.
- After an unknown or ambiguous paid submission, this is the recovery path: match the model slug and timestamp in history, confirm with
task get, and only submit again once you are sure nothing was accepted. - For any task that reached a successful terminal state, hand off to
/modellix:download— resource URLs expire in about 7 days. - Report each task's id, model slug, status, and the next action.
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 · 35 lines · 15 tokens per session scan A 2b413439b53d
tasks is a command published in the GitHub repository Modellix/modellix-plugin (1 stars, last pushed 20d ago), licensed MIT. It adds 15 tokens to every session and 303 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
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
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.
ghost-decode
Decode a ghost-font video and reveal the hidden text.