ToolUniverse is a collection of tools, interfaces, and supporting components for building AI systems that perform scientific work. It is for developers creating AI scientist agents that use APIs, databases, machine-learning tools, and domain-specific utilities. The catalogue includes skills, commands, an MCP server, an agent, and a hook for working with the ecosystem.
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 mims-harvard/ToolUniverse --skill tooluniverse-protein-design-campaigngit clone --depth 1 https://github.com/mims-harvard/ToolUniverseWrote 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/mims-harvard/tooluniverse/tooluniverse-protein-design-campaign)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-protein-design-campaign"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-protein-design-campaign/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/mims-harvard/tooluniverse/tooluniverse-protein-design-campaign"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-protein-design-campaign.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 | $0.00063 | $0.01233 |
| Opus 5.5 | $0.00025 | $0.00493 |
| Sonnet 5.5 | $0.00013 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00123 |
Grade A, and why
tooluniverse-protein-design-campaign 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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protein Design Campaign
Turn an ongoing binder-design effort into reproducible candidate decisions and an honestly described experimental or competition submission. Preserve the user's chosen models, infrastructure and goals; this skill does not grant permission to upload unpublished designs, publish a repository or accept terms.
Establish the current decision
For an existing campaign, read its latest status, manifests, executed results and failure records before launching jobs. Distinguish a completed process from an active one; an old PID or a queued browser file is not proof of ongoing computation or submission.
Record target isoform/species, assay construct and termini, intended epitope, glycosylation assumptions, molecule class, designable positions, and objective direction. Explicitly distinguish stronger binding at acidic pH from binding at neutral pH with acidic release. They are different objectives, not interchangeable consequences of adding histidine.
For competitions, verify the live challenge, account track, deadlines, novelty definition and molecule formats. Convert the deadline with an explicit UTC offset; AoE means UTC−12. Keep current competition limits in the campaign record, not as permanent defaults in this skill.
Choose the next informative computation
- Resolve execution or input defects before generating more designs. Missing atoms, misidentified glycans or incomplete pKa inventories invalidate downstream scores.
- Test known positive controls through the same preparation and scoring pipeline. If a known binder fails, diagnose the pipeline before treating the cutoff as a candidate veto. Keep the original result and any revised criterion separate.
- Spend compute on distinct uncertainty: foldability, complex pose, receptor/glycan compatibility, protonation mechanism, or cross-species compatibility. More seeds assess sampling but do not supply another model family.
- When models disagree, compare constructs, component retention, protonation conventions and coordinate preparation. Do not average unrelated units into an apparent consensus.
- Keep an experimental route visible: matched SPR/BLI or an equivalent binding assay at the specified pHs, with receptor species and construct controls. Computation cannot establish an assay detection threshold.
What ships with it
6 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.
- 9d ago First seen · 70 lines · 63 tokens per session scan A 1dce2725004b
tooluniverse-protein-design-campaign is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 63 tokens to every session and 1,233 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-08.
Other skills, from other repositories
ai-agent-tool-routing
Use when designing or reviewing an AI agent tool registry or MCP router: document parameter schemas, caller authorization, execution limits, replay-safe retries and verification evidence.
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
construct-toy-examples
Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. Use when you are stuck in reasoning and need simpler examples to regain traction, or when you want to see where the assumptions take effect and gain intuition.
obtain-immediate-conclusions
Derive immediate mathematical consequences from a theorem statement or subgoal. Use when starting a new problem, branch, or subgoal, or when cheap progress or a cleaner reformulation is needed before deeper proof search.
clinical-research-analysis-framework
Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.
apache-iv-score
Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.