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 skills add burin-labs/harn --skill harn-providersgit clone --depth 1 https://github.com/burin-labs/harnWrote 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/skills/burin-labs/harn/harn-providers)<a href="https://agentmods.dev/skills/burin-labs/harn/harn-providers"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-providers/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/skills/burin-labs/harn/harn-providers"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-providers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.01450 |
| Opus 5 | $0.00013 | $0.00725 |
| Sonnet 5 | $0.00005 | $0.00290 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
harn-providers 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harn providers
Use this skill when wiring or debugging LLM providers, model routes, structured output, connector providers, or provider readiness.
Pair it with [[harn-orchestration]] for workflow behavior and [[harn-testing]] for deterministic provider fixtures.
Start here
docs/llm/harn-quickref.mddocumentsllm_callandllm_stream_call.- The quickref also covers
provider: "auto", schemas, and retries. docs/llm/harn-triggers-quickref.mddocuments connector provider manifests.- LLM configuration and routing live under
crates/harn-vm/src/. - Package/provider manifest handling lives under
crates/harn-cli/src/package/. - Provider capability rows are surfaced by CLI matrix commands.
- Mock providers are the default for deterministic tests.
- Never require live credentials in ordinary CI.
llm_call options
- Keep
providerexplicit when behavior depends on a vendor. - Use
provider: "auto"only when capability-based routing is acceptable. - Keep
modeloptional only when routing policy can choose safely. - Express structured output through
output:"json", a schema, or{schema, strict?, validation?, stream_abort?}. - Preserve
schema_retriesandrepairbehavior. - Compose system text with the single
systemstring-or-fragment-list option. - Use
effortandspeedfor provider-neutral intent. - Use
timeout_msandidle_timeout_ms; both are milliseconds. - Put wire-specific fields below
provider_options.<provider>. - Treat portable generation options as required caller intent. An authored
capability denial is a terminal
invalid_request; adapters must not drop it. - Unknown custom generation routes remain open-world. Explicit
cache: trueandprompt_cache_ttlrequire authored support because cache lowering is provider-specific; TTL values must be listed inprompt_cache_ttls. - Let
cache_breakpoint_stylechoose the request marker location. Provider adapters must use the canonical lowering and preserve explicit caller markers. - Keep provider tool execution distinct with
provider_tools. - Preserve tool-call format negotiation and cost controls.
- Preserve mock-provider determinism.
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.
- 10d ago First seen · 139 lines · 25 tokens per session scan A 943efde1fa4a
harn-providers is a skill published in the GitHub repository burin-labs/harn (21 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 1,450 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 2026-08-30.
Other skills, from other repositories
archestra-dev-llm-providers
Use when adding an LLM provider, changing proxy adapters or provider routes, fixing streaming/tool-call translation bugs, editing model fetchers or model handling, or touching provider credentials/enums and model constants.
translate
A translation tool for converting user-provided text between languages, with Chinese and English as the default pair.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
thinking-out-loud
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
hugging-face-datasets
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.