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 ericrisco/rsc-harness --skill open-weightsgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/open-weights)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/open-weights"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/open-weights.svg" alt="Measured on agentmods" 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 | $0.00146 | $0.04580 |
| Opus 5 | $0.00073 | $0.02290 |
| Sonnet 5 | $0.00029 | $0.00916 |
| Haiku 4.5 | $0.00015 | $0.00458 |
Grade A, and why
open-weights 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 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.
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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open weights — pick the model, then clear the license
This is the CHOICE layer. Given a task, a box, and a shipping constraint, it tells you which open model to reach for and whether the license lets you ship it. It does not download, run, serve, or fine-tune anything — it feeds the skills that do (see Related skills).
The one rule (read before you name a model)
Model names and their licenses change monthly. Never state a license from memory — open the model card and confirm it, every time. This file was authored against cards live in mid-2026; by the time you read it, versions have shipped and terms have moved. So:
- Treat every specific version/license line below as [verify the card], not as settled fact.
- State the license class (OSI-open vs custom-community vs restricted), then send the reader to
the actual
LICENSE/ terms page for the exact model + size they intend to ship. - The decision framework and the class taxonomy are the durable parts. The version list is the perishable part. Weight your trust accordingly.
Real, verified-mid-2026 examples of why this rule exists — all confirmed against the source, and all things that were different at my Jan-2026 cutoff:
- Gemma 4 moved to Apache-2.0, while Gemma 1–3 stay on the custom Gemma Terms of Use (confirmed on ai.google.dev/gemma/terms, accessed 2026-07-18). Same brand, opposite license class depending on version.
- Codestral 2 was relicensed Apache-2.0 (per Mistral, Apr 2026), while the original Codestral stays non-production (MNPL). Same name, opposite shippability depending on release.
- DeepSeek-R1 is MIT, but the original DeepSeek-V3 weights ship under a custom DeepSeek License Agreement with OpenRAIL-style use restrictions (confirmed on the V3 LICENSE-MODEL), not MIT. Same family, different license per model.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 240 lines · 146 tokens per session scan A e628511e0b4a
open-weights is a skill published in the GitHub repository ericrisco/rsc-harness (70 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 4,580 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
attach-receipts
Attaches sourcedoc/extractionrunid/schemaversion receipts to every edge at write time, and refuses to write any edge missing one of the three.
supersede-claim
Corrects a wrong claim by adding a new node holding the correction and a supersedes edge back to the old node, which stays in the graph flagged stale rather than being edited or deleted.
ai-policy-generator
AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.
graphify
Turn any folder of files (code, docs, papers, images, video) into a queryable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md. Use when asked to analyze a codebase, understand architecture, map dependencies…
assessing-vector-and-embedding-weaknesses
Test vector stores for embedding inversion, cross-tenant leakage, and poisoning.
detecting-data-and-model-poisoning
Identify poisoned training data and backdoored models across the ML pipeline.