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/stratalab/strata-coreWrote 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/stratalab/strata-core/inference.status)<a href="https://agentmods.dev/commands/stratalab/strata-core/inference.status"><img src="https://agentmods.dev/badge/commands/stratalab/strata-core/inference.status/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/stratalab/strata-core/inference.status"><img src="https://agentmods.dev/badge/commands/stratalab/strata-core/inference.status.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 | $0.00426 |
| Opus 5 | $0.00000 | $0.00213 |
| Sonnet 5 | $0.00000 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
inference.status 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 2d 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.
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
Reports the inference facts that are knowable up front: whether this build can execute local models and download them, which providers are compiled in, which of those have an API key and where it was found, and how many catalogued models are already on disk.
Released binaries ship the cloud providers and leave local model execution out, so local_execution is false in them and every catalogued local model is unavailable until strata inference install-local adds it; local_remedy says so. Knowing that from status is the point: previously the only way to find out was to run an operation and read the failure.
key_source names where a key was read from: the environment variable, or the config file's path when the key was set with strata config set <provider>.api_key. The runtime asks the environment first and the config file second, and reports the one that answered, so key_source is exactly what a generate or embed call would use. The key itself is never returned.
base_url is the endpoint a call to the provider would reach, and base_url_source names what redirected it: the provider's own environment variable (base_url_env_var — OPENAI_BASE_URL, ANTHROPIC_BASE_URL, GOOGLE_GEMINI_BASE_URL, with the same meaning as in each provider's SDK), or the config file's path when it was set with strata config set <provider>.base_url. The environment wins over the file, as for a key. When neither is set, base_url is the provider's public endpoint and base_url_source is absent. A provider that is not reached over HTTP reports none of the three.
The model directory is shared by every database on the machine, so a model downloaded once is available to all of them.
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.
- 2d ago Changed · +2 lines e26b9e305151
- 4d ago First seen · 13 lines · 0 tokens per session scan A f6177556faca
inference.status is a command published in the GitHub repository stratalab/strata-core (2 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 426 tokens. 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 2026-09-09.
Other commands, from other repositories
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
laravel-ai-sdk
Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
dare-llm-integration
Integração segura e eficiente com LLMs (Gemini, Claude, OpenAI, Ollama) em projetos DARE.
prompt-create
Create a new prompt following ground rules.