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-synthetic-biology-partsgit 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-synthetic-biology-parts)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-synthetic-biology-parts"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-synthetic-biology-parts/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-synthetic-biology-parts"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-synthetic-biology-parts.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 | $0.00000 | $0.01876 |
| Opus 5.5 | $0.00000 | $0.00750 |
| Sonnet 5.5 | $0.00000 | $0.00375 |
| Haiku 4.5 | $0.00000 | $0.00188 |
Grade A, and why
tooluniverse-synthetic-biology-parts 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthetic Biology Parts Lookup (SynBioHub)
Search and retrieve genetic parts — promoters, ribosome binding sites (RBS), coding sequences, terminators, reporters, and composite genetic devices — from SynBioHub, the standard synthetic-biology parts repository that hosts the iGEM Registry of Standard Biological Parts (20,000+ BioBricks), CIDAR Lab parts, Free Genes libraries, and other public SBOL collections.
Honesty contract (read first) — verify auth status before promising results
Live-verified as of this writing: every anonymous call to all 3 tools below fails. SynBioHub disabled anonymous access to its public REST endpoints upstream. Confirmed by actually running each tool with no token set:
$ tu run SynBioHub_get_collections '{}'
Error: SynBioHub API HTTP error: 401 (login required). synbiohub.org now
requires an authenticated session for this endpoint (no SYNBIOHUB_API_TOKEN
is set). Log in at synbiohub.org, then set SYNBIOHUB_API_TOKEN to the
session token to retry.
$ tu run SynBioHub_search_parts '{"query": "GFP"}'
Error: SynBioHub API HTTP error: 401 (login required). ...
$ tu run SynBioHub_get_part '{"display_id": "BBa_E0040"}'
Error: SynBioHub did not return SBOL/XML data for
'https://synbiohub.org/public/igem/BBa_E0040/1' (got non-XML content, likely
an HTML login or error page). The part may not exist, or SynBioHub may now
require authentication for this request.
Before using this skill, always try one call first (e.g.
SynBioHub_get_collections with no arguments — cheapest possible check).
If it returns a 401/login-required error:
- Tell the user plainly: SynBioHub now requires authentication for these reads; this is an upstream policy change, not a bug in the request.
- Point them to create a free account at https://synbiohub.org, log in,
and retrieve a session token, then set
SYNBIOHUB_API_TOKENin the environment before retrying. - Never fabricate a part record, sequence, or collection list to work around the error. If the token isn't available, say the lookup cannot be completed right now — do not guess a BioBrick's sequence from training-data memory and present it as a live SynBioHub result.
What ships with it
1 file 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.
- 10d ago First seen · 146 lines · 0 tokens per session scan A f9c3494411ad
tooluniverse-synthetic-biology-parts is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,876 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 2026-10-07.
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.