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.
git clone --depth 1 https://github.com/Modellix/modellix-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/modellix/modellix-plugin/download)<a href="https://agentmods.dev/commands/modellix/modellix-plugin/download"><img src="https://agentmods.dev/badge/commands/modellix/modellix-plugin/download/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/modellix/modellix-plugin/download"><img src="https://agentmods.dev/badge/commands/modellix/modellix-plugin/download.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00325 |
| Opus 5.5 | $0.00000 | $0.00130 |
| Sonnet 5.5 | $0.00000 | $0.00065 |
| Haiku 4.5 | $0.00000 | $0.00032 |
Grade A, and why
download 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. If the download fails with a private or reserved network error (common when a local proxy maps `file.modellix.ai` into `198.18.0.0/15`), retry with `--allow-private-network` for trusted Modellix CDN hosts, or fetch `r What it actually says
Download Modellix results. Target: $ARGUMENTS
Read-only against the API: downloading costs nothing and never resubmits a task.
- Resolve the task id: use the one in
$ARGUMENTS, otherwise take the most recent successful entry frommodellix-cli task history --limit 20 --jsonand say which one you picked. - Download to
./outputsunless$ARGUMENTSnames a directory:
modellix-cli task download <task_id> --output-dir ./outputs --json
Existing files are preserved by default; pass --overwrite only when the user asks for it.
- If the task is not in a successful terminal state yet, stop and use
/modellix:tasksto wait — do not submit a new task. - If the download fails with a private or reserved network error (common when a local proxy maps
file.modellix.aiinto198.18.0.0/15), retry with--allow-private-networkfor trusted Modellix CDN hosts, or fetchresult.resources[].urlwith curl and name filesmodellix-{model_slug}-{timestamp}.{ext}(slashes in the slug become hyphens). - Resource URLs expire in about 7 days. If they are already gone, say so plainly instead of silently regenerating.
- Report the local file paths and byte counts.
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.
- 1mo ago First seen · 23 lines · 0 tokens per session scan A 25a8911c52d5
download is a command published in the GitHub repository Modellix/modellix-plugin (1 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 325 tokens. 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
i-have-adhd
Shape output for a reader with ADHD for the rest of this session.
lessons-compact
Compact MEMORY/LESSON.md by deduplicating near-identical lessons, merging same-root-cause lessons, and pruning stale ones — without losing any unique signal. Delegates the analysis to the lessons-compactor agent.
prompt-history
Manage history of created and optimized prompts.
lessons
View project lessons in MEMORY/LESSON.md (project root) and append a compact "never reproduce" lesson.
tldr
Compress what was just said into a TLDR. /tldr for the last reply, /tldr session for everything since the session started.
on
Turn on senior mode — refuses vague questions, hints instead of answers, never writes code.