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 devtu-code-optimizationgit 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/devtu-code-optimization)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/devtu-code-optimization"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/devtu-code-optimization/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/devtu-code-optimization"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/devtu-code-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 6 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Tool Misuse · line 49 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00087 | $0.00793 |
| Opus 5.5 | $0.00035 | $0.00317 |
| Sonnet 5.5 | $0.00017 | $0.00159 |
| Haiku 4.5 | $0.00009 | $0.00079 |
Grade A, and why
devtu-code-optimization 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ToolUniverse Code Optimization
Always run Skill(skill="simplify") after writing or modifying code.
Pre-Commit Checklist
-
return_schemahasoneOf: [{data+metadata}, {error}] - Test examples use real IDs (no DUMMY/PLACEHOLDER)
-
try:hasexcept:at exact same indentation level - No trailing commas in JSON (
python3 -c "import json; json.load(open('f.json'))") - New tool class registered in
_lazy_registry_static.pyanddefault_config.py -
ruff check src/tooluniverse/<file>.pypasses -
python -c "from tooluniverse.<module> import <Class>"passes -
python -m tooluniverse.cli run <Tool> '<real_args_json>'returns expected data - Ran
Skill(skill="simplify")on all modified files
Key Fix Categories
| Category | Signal | Reference |
|---|---|---|
| Silent param ignored | API accepts but drops filter | code-patterns.md — Client-Side Filter |
| Wrong API field/endpoint | 0 results or 404 | api-fixes.md — Quick Lookup Table |
| Schema invalid | null type, missing oneOf | code-patterns.md — Schema Patterns |
| Undisclosed normalization | Auto-transform hidden from user | code-patterns.md — Normalization Disclosure |
| try/except indent | SyntaxError at runtime | code-patterns.md — try/except section |
| Truncation buried | Data count hidden in notes | code-patterns.md — Truncation |
| Hosted model API (NIM) | async 404 on poll, JSON-wrapped output, 200+inner-failure, "not found for account" | code-patterns.md — Hosted Model-API Tools |
| R subprocess tool | '\.' unrecognized escape from Rscript -e |
code-patterns.md — R-subprocess Tools |
References
- references/api-fixes.md — Per-API bug fixes (GtoPdb, CIViC, GTEx, ENCODE, CPIC, etc.)
- references/code-patterns.md — Reusable Python patterns (schema, filtering, pagination, normalization)
What ships with it
2 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 Changed 7adbca637263
- 1mo ago First seen · 58 lines · 87 tokens per session scan A d720f25cac5f
devtu-code-optimization is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,739 stars, last pushed today), licensed Apache-2.0. It adds 87 tokens to every session and 793 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
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
bug-fixing
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.
python-testing
Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.