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/druide67/asiai/configgit clone --depth 1 https://github.com/druide67/asiaiWrote 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/druide67/asiai/config)<a href="https://agentmods.dev/commands/druide67/asiai/config"><img src="https://agentmods.dev/badge/commands/druide67/asiai/config.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00777 |
| Opus 5 | $0.00012 | $0.00388 |
| Sonnet 5 | $0.00005 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade B, and why
config 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ~/.config/asiai/keys/mtplx.key How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
asiai config
Manage persistent engine configuration. Engines discovered by asiai detect are automatically saved to ~/.config/asiai/engines.json for faster subsequent detection.
Usage
asiai config show # Show known engines
asiai config add <engine> <url> [--label NAME] [--api-key-file PATH] # Add engine manually
asiai config remove <url> # Remove an engine
asiai config reset # Clear all configuration
Subcommands
show
Display all known engines with their URL, version, source (auto/manual), and last seen timestamp.
$ asiai config show
Known engines (3):
ollama v0.17.7 at http://localhost:11434 (auto) last seen 2m ago
lmstudio v0.4.6 at http://localhost:1234 (auto) last seen 2m ago
omlx v0.9.2 at http://localhost:8800 [mac-mini] (manual) last seen 5m ago
add
Manually register an engine on a non-standard port. Manual engines are never auto-pruned.
asiai config add omlx http://localhost:8800 --label desktop
asiai config add ollama http://192.0.2.10:11434 --label remote
asiai config add mtplx http://localhost:8080 --api-key-file ~/.config/asiai/keys/mtplx.key
Engine API keys (--api-key-file)
Some servers require Authorization: Bearer <key> on every route (for example MTPLX started with an API key, or llama.cpp with --api-key). Point the engine entry at a file containing the key — the key itself is never stored in the config:
{
"url": "http://localhost:8080",
"engine": "mtplx",
"source": "manual",
"api_key_file": "/path/to/mtplx.key"
}
When api_key_file is set, asiai sends the Bearer header on every request to that engine's URL only — detection probes, monitoring, the web dashboard, and benchmarks. If the file is missing, unreadable, or empty, requests are sent without the header and the server's 401 surfaces honestly. The key is never written to logs or error messages.
Keep the key file readable only by your user:
chmod 600 ~/.config/asiai/keys/mtplx.key
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.
- 4d ago First seen · 89 lines · 24 tokens per session scan B 5ad9d6109c6c
config is a command published in the GitHub repository druide67/asiai (11 stars, last pushed 4d ago), licensed Apache-2.0. It adds 24 tokens to every session and 777 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
perfup
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR.
integrate-pipeline
Integrate a new document parsing pipeline into ParseBench: $ARGUMENTS.
netllm-setup
First-time netllm install from this repo (uv sync, init, discover, verify).
netllm-swarm
Configure multi-machine LAN mesh for netllm (mDNS, peers, gateway).
/opsx-explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
/opsx-propose
Propose a new change - create it and generate all artifacts in one step.