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 agentmods add skills/zaoqu-liu/scienceclaw/devtu-create-toolnpx skills add Zaoqu-Liu/ScienceClaw --skill devtu-create-toolgit clone --depth 1 https://github.com/Zaoqu-Liu/ScienceClawWrote 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/zaoqu-liu/scienceclaw/devtu-create-tool)<a href="https://agentmods.dev/skills/zaoqu-liu/scienceclaw/devtu-create-tool"><img src="https://agentmods.dev/badge/skills/zaoqu-liu/scienceclaw/devtu-create-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 | $0.00075 | $0.06460 |
| Opus 5 | $0.00037 | $0.03230 |
| Sonnet 5 | $0.00015 | $0.01292 |
| Haiku 4.5 | $0.00007 | $0.00646 |
Grade C, and why
devtu-create-tool scanned grade C with 2 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 3d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s https://pypi.org/pypi/PACKAGE/json | python3 -c " Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.get( How it starts
The opening of the file, as written. The whole thing — 950 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ToolUniverse Tool Creator
Create new scientific tools for the ToolUniverse framework following established best practices.
Table of Contents
- Critical Knowledge
- Core Concepts
- Implementation Guide
- Testing Strategy
- Common Patterns
- Troubleshooting
- Reference
Critical Knowledge
Top 7 Mistakes (90% of Failures)
- Missing
default_config.pyEntry - Tools silently won't load - Non-nullable Mutually Exclusive Parameters - Validation errors (NEW #1 issue in 2026)
- Fake test_examples - Tests fail, agents get bad examples
- Single-level Testing - Misses registration bugs
- Skipping
test_new_tools.py- Misses schema/API issues - Tool Names > 55 chars - Breaks MCP compatibility
- Raising Exceptions - Should return error dicts instead
Most Common (2026): Mistake #2 affects 60% of new tools. Always make mutually exclusive parameters nullable: {"type": ["string", "null"]}
Tool Creator vs SDK User
| SDK User (Using) | Tool Creator (Building) |
|---|---|
tu.tools.ToolName() |
@register_tool() + JSON |
| Handle responses | Design schemas |
| One-level usage | Three-step registration |
Core Concepts
Two-Stage Architecture
Stage 1: Tool Class Stage 2: Wrappers (Auto-Generated)
Python Implementation From JSON Configs
↓ ↓
@register_tool("MyTool") MyAPI_list_items()
class MyTool(BaseTool): MyAPI_search()
def run(arguments): MyAPI_get_details()
Key Points:
- One class handles multiple operations
- JSON defines individual tool wrappers
- Users call wrappers, which route to class
- Need BOTH for tools to work
Three-Step Registration
Step 1: Class Registration
@register_tool("MyAPITool") # Decorator registers class
class MyAPITool(BaseTool):
pass
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.
- 3d ago First seen · 950 lines · 75 tokens per session scan C 71634d297135
devtu-create-tool is a skill published in the GitHub repository Zaoqu-Liu/ScienceClaw (59 stars, last pushed 5mo ago), licensed MIT. It adds 75 tokens to every session and 6,460 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
extracting-pii-entities
Detect PHI/PII spans in clinical text with OpenMed's extractpii without altering the text. Use when the user wants to find names, dates, MRNs, phone numbers, addresses, SSNs, or other identifiers and get their offsets and labels (not redact them), inspect what would be removed before de-identifying, route spans to a…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.
tooluniverse-electron-microscopy
Search and analyze electron microscopy data — cryo-EM density maps (EMDB), fitted atomic models (PDB), raw micrograph datasets (EMPIAR), and cryo-electron tomography volumes (CryoET Data Portal). Use for finding 3D structural data on a protein/complex, comparing experimental EM resolution to AlphaFold confidence, and…
tooluniverse-drug-research
Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory…