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
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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-fix-tool)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/devtu-fix-tool"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/devtu-fix-tool.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 | $0.00057 | $0.03469 |
| Opus 5 | $0.00028 | $0.01734 |
| Sonnet 5 | $0.00011 | $0.00694 |
| Haiku 4.5 | $0.00006 | $0.00347 |
Grade A, and why
devtu-fix-tool 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- devtu-fix-tool — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix ToolUniverse Tools
Diagnose and fix failing ToolUniverse tools through systematic error identification, targeted fixes, and validation.
First Principles for Bug Fixes
Before writing any fix, ask: why does the user reach this failure state?
- Prevent, don't recover — fix the root cause so the failure can't happen, rather than adding hint text after it does
- Validate at input, not at output — wrong parameters, unknown disease names, unsupported drugs should be caught and rejected early with clear guidance, not discovered after a silent API call
- Don't mask silent mutations — if input is auto-normalized (fusion notation, Title Case), either accept both forms natively OR reject with explicit guidance; never silently transform and hide it
- Distinguish "no data" from "bad query" — zero results because the filter is wrong is different from zero results because the data doesn't exist; the response must distinguish these clearly
- Fix the abstraction, not the instance — if a parameter name is inconsistent, fix the interface; don't add an alias list that grows forever
Anti-patterns to avoid:
- Adding hint text to zero-result messages instead of validating upfront
- Adding parameter aliases instead of fixing naming consistency
- Post-hoc probing to rescue a failed query instead of pre-validating
Bug Verification (CRITICAL)
Before implementing any bug report, verify it via CLI first:
python3 -m tooluniverse.cli run <ToolName> '<json_args>'
Many agent-reported bugs are false positives caused by MCP interface confusion. Always confirm the bug is reproducible before implementing a fix.
Instructions
When fixing a failing tool:
- Run targeted test to identify error:
python scripts/test_new_tools.py <tool-pattern> -v
-
Verify API is correct - search online for official API documentation to confirm endpoints, parameters, and patterns are correct
-
Identify error type (see Error Types section)
What ships with it
3 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.
- 2d ago First seen · 389 lines · 57 tokens per session scan A 7ba96426db25
devtu-fix-tool is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,672 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 3,469 once invoked, about $0.0003 per session on Opus 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
adk-debug
Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the adk run CLI and the adk web dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the wrong answer, ignores a tool or swallows a tool error, hangs…
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
trulens-diagnosis
Diagnose low evaluation scores and generate actionable improvement recommendations.
ax-cpp-agent-observability
Use when writing C++ code with axllm for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.