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 ma-compbio-lab/SkillFoundry --skill benchmarks-and-evaluation-startergit clone --depth 1 https://github.com/ma-compbio-lab/SkillFoundryWrote 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/ma-compbio-lab/skillfoundry/benchmarks-and-evaluation-starter)<a href="https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/benchmarks-and-evaluation-starter"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/benchmarks-and-evaluation-starter.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 5.1 | $0.00000 | $0.00155 |
| Opus 5 | $0.00000 | $0.00077 |
| Sonnet 5 | $0.00000 | $0.00031 |
| Haiku 4.5 | $0.00000 | $0.00015 |
Grade A, and why
benchmarks-and-evaluation-starter 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 8d 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
Benchmarks and evaluation Starter
Use this starter when a task lands in the Benchmarks and evaluation frontier leaf and the repository has curated resources but no dedicated runtime implementation yet.
What this starter does
- Summarizes the local resource anchors for the leaf.
- Emits a machine-readable starter plan with promotion steps.
- Gives the agent a stable local entry point before a full runtime skill exists.
How to use it
Run python3 skills/drug-discovery-and-cheminformatics/benchmarks-and-evaluation-starter/scripts/run_frontier_starter.py --out scratch/frontier/benchmarks-and-evaluation-starter.json.
Then inspect refs.md and examples/resource_context.json to promote the starter into a concrete executable workflow.
What ships with it
7 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.
- 8d ago First seen · 17 lines · 0 tokens per session scan A 42acf21c0f94
benchmarks-and-evaluation-starter is a skill published in the GitHub repository ma-compbio-lab/SkillFoundry (38 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 155 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 2026-08-30.
Other skills, from other repositories
arxiv-search
Skill "arxiv-search" from TaewoooPark/MagLab, covering category scoping, query families (3–6 per topic), version and doi resolution, tier classification and output contract.
academic-email
Professional academic email workflow (≤200 words). Invokes AcademicEmailAgent to draft a concise email with subject line and follow-up action for one of five standard email types: collaboration, question, interview, recommendation, or application. Output carries HUMAN REVIEW REQUIRED; no auto-send (§16.3).
cover-letter
Journal submission cover letter workflow (≤250 words). Invokes CoverLetterAgent to draft a concise novelty-focused cover letter from the author's key results. Output carries HUMAN REVIEW REQUIRED; no auto-send. All personal/institutional fields are marked [FILL] for the author to complete (§16.3).
literature-review
Systematic literature review workflow — search → screening → quality assessment → topic-centred synthesis. Includes local-gap analysis. A DOI citation is required for every factual claim (§14.7). Activated by the maglab lit search command and the synthesis-editor agent.
literature-search
Broad literature search for magnetism & spintronics — OpenAlex REST query strategy, query family generation, tier classification, and evidencematrix construction (§14.3·§14.7). Activated by the maglab lit search command and the research orchestration search-scout agent.
revision-letter
Point-by-point peer-review response letter workflow for journal resubmission. Invokes RevisionLetterAgent to quote each reviewer comment verbatim, draft a response, and add a change-location marker. Outputs carry HUMAN REVIEW REQUIRED; no auto-send. A DOI or manuscript location is required for every factual response…