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-immunotherapy-response-predictiongit 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-immunotherapy-response-prediction)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-immunotherapy-response-prediction"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-immunotherapy-response-prediction/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-immunotherapy-response-prediction"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-immunotherapy-response-prediction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00081 | $0.02750 |
| Opus 5.5 | $0.00032 | $0.01100 |
| Sonnet 5.5 | $0.00016 | $0.00550 |
| Haiku 4.5 | $0.00008 | $0.00275 |
Grade A, and why
tooluniverse-immunotherapy-response-prediction 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 1mo 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Immunotherapy Response Prediction
Predict patient response to immune checkpoint inhibitors (ICIs) using multi-biomarker integration. Transforms a patient tumor profile (cancer type + mutations + biomarkers) into a quantitative ICI Response Score with drug-specific recommendations, resistance risk assessment, and monitoring plan.
Reasoning Before Searching
Not all tumors respond to checkpoint inhibitors. Reason through the biology before running tools:
- TMB (tumor mutational burden): More somatic mutations produce more neoantigens, which are recognized by T cells. High TMB (>=10 mut/Mb, FDA-approved threshold for pembrolizumab) generally predicts better response — but this varies by cancer type (e.g., RCC responds despite low TMB).
- MSI-H (microsatellite instability-high): Caused by defective DNA mismatch repair (MMR). MSI-H tumors have very high TMB and are pan-cancer approved for pembrolizumab. Check MLH1, MSH2, MSH6, PMS2 mutations.
- PD-L1 expression: The direct target of pembrolizumab/atezolizumab. High PD-L1 (TPS >=50% or CPS >=10 depending on cancer) predicts response in some cancers (NSCLC) but not all (melanoma, where TMB is more predictive).
- Resistance factors are equally important: STK11, KEAP1, JAK1/2 loss, B2M mutations can render an otherwise TMB-high tumor non-responsive.
Before calling any tool, determine which biomarkers are available for this patient and which are unknown. This determines which phases can be scored with data vs. must use cancer-type priors. Do not default to "moderate" for unknowns — flag them explicitly as missing.
LOOK UP DON'T GUESS: Never assume FDA approval for a biomarker-ICI combination — always verify with fda_pharmacogenomic_biomarkers or FDA_get_indications_by_drug_name. Cancer-specific thresholds differ from pan-cancer approvals.
KEY PRINCIPLES:
- Report-first approach - Create report file FIRST, then populate progressively
- Evidence-graded - Every finding has an evidence tier (T1-T4)
- Quantitative output - ICI Response Score (0-100) with transparent component breakdown
- Cancer-specific - All thresholds and predictions are cancer-type adjusted
- Multi-biomarker - Integrate TMB + MSI + PD-L1 + neoantigen + mutations
- Resistance-aware - Always check for known resistance mutations (STK11, PTEN, JAK1/2, B2M)
- Drug-specific - Recommend specific ICI agents with evidence
- Source-referenced - Every statement cites the tool/database source
- English-first queries - Always use English terms in tool calls
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.
- 1mo ago First seen · 209 lines · 81 tokens per session scan A cb7ea2d8391a
tooluniverse-immunotherapy-response-prediction is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 81 tokens to every session and 2,750 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 2026-09-03.
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.