translate-id

translate-id is a command for Claude Code from mims-harvard/ToolUniverse. It costs 85 tokens per session (1,533 once invoked), scanned A, original, Apache-2.0.

A command for converting an identifier from one biological database system to matching identifiers in others, such as gene, protein, disease, or compound databases.

In plain words
What is it for?
Recognizing identifiers, resolving cross-references, and producing a table linking genes, proteins, diseases, variants, and chemicals across databases.
Why use it?
It avoids failed lookups caused by sending an identifier to a tool that expects a different format.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the tooluniverse plugin — 140 skills, 8 commands, 1 agent, 1 hook, 1 MCP server shipped together

Good fit Recognizing identifiers, resolving cross-references, and producing a table linking genes, proteins, diseases, variants, and chemicals across databases.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mims-harvard/tooluniverse/translate-id
About the project

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.

mims-harvard/ToolUniverse · 1,676 stars · on GitHub · aiscientist.tools

Install

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.

Clone the repo
git clone --depth 1 https://github.com/mims-harvard/ToolUniverse

Made for: Claude Code.

Or install tooluniverse, the plugin that ships this one along with the rest of its 140 skills, 8 commands, 1 agent, 1 hook, 1 MCP server.

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.

agentmods badge for translate-id

README.md
[![agentmods](https://agentmods.dev/badge/commands/mims-harvard/tooluniverse/translate-id/github.svg)](https://agentmods.dev/commands/mims-harvard/tooluniverse/translate-id)
Your own site
<a href="https://agentmods.dev/commands/mims-harvard/tooluniverse/translate-id"><img src="https://agentmods.dev/badge/commands/mims-harvard/tooluniverse/translate-id/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.

agentmods 80×15 button for translate-id

Your own site · 80×15
<a href="https://agentmods.dev/commands/mims-harvard/tooluniverse/translate-id"><img src="https://agentmods.dev/badge/commands/mims-harvard/tooluniverse/translate-id.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,533 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.01533
Opus 5 $0.00043 $0.00766
Sonnet 5 $0.00017 $0.00307
Haiku 4.5 $0.00009 $0.00153

Measured 9d ago against content hash c80621d234cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

translate-id 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.

plugin/commands/translate-id.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Translate this identifier across namespaces: $ARGUMENTS

Direct ID lookup is brittle: each tool expects its own namespace, and silently returns nothing if you pass the wrong one. Detect, route, and report.

Process

1. Detect input namespace

Inspect the identifier shape:

Pattern Namespace
^ENS[GTPR]\d+(\.\d+)?$ Ensembl gene/transcript/protein/RefSeq
^[OPQ][0-9][A-Z0-9]{3}[0-9]$ or ^[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}$ UniProt accession
^NM_\d+(\.\d+)?$, ^NP_, ^XM_ RefSeq
^\d+$ (numeric only) likely NCBI Gene ID — confirm via metadata
^OMIM:\d+$ or ^\d{6}$ (6-digit) OMIM
^MGI:\d+$ MGI
^CHEMBL\d+$ ChEMBL
^CID\d+$ or ^\d+$ in chemistry context PubChem CID
^DB\d{5}$ DrugBank
^MONDO:\d+$, ^DOID:\d+$, ^EFO:\d+$ ontology disease IDs
^rs\d+$ dbSNP
All-caps, 1-10 chars, no digits likely HGNC gene symbol
Free-form name drug name / disease name — fuzzy lookup

If ambiguous (e.g., "BRAF" could be gene OR drug target context), ASK the user or pick gene by default and note the assumption.

2. Pick the resolver

For genes/proteins:

  • HGNC symbol → all → tu run MyGene_query_genes '{"query":"<symbol>","species":"human"}' (returns Ensembl, UniProt, RefSeq, NCBI Gene, MGI in one call)
  • Ensembl ID → all → tu run ensembl_lookup_gene '{"gene_id":"<id>"}'
  • UniProt → gene/Ensembl → tu run UniProt_search '{"query":"<accession>","limit":1}'
  • NCBI Gene ID → all → tu run NCBIGene_get_summary '{"id":"<id>"}' then chain

For chemicals:

  • Drug name → all → tu run ChEMBL_search_molecules '{"query":"<name>","limit":1}' then tu run PubChem_get_CID_by_name for cross-ref
  • ChEMBL ID → all → get_tool_info to find the right cross-ref tool

For diseases:

  • Disease name → MONDO/DOID/EFO/OMIM → tu run ols_search_terms '{"query":"<name>","ontologies":["mondo","doid","efo"]}'
  • OMIM → MONDO → tu run MONDO_search (if available) or ols_search_terms

Read the full file on GitHub · 112 lines

Changes

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.

  1. 9d ago First seen · 112 lines · 85 tokens per session scan A c80621d234cb

Subscribe to this mod's changes

translate-id is a command published in the GitHub repository mims-harvard/ToolUniverse (1,676 stars, last pushed yesterday), licensed Apache-2.0. It adds 85 tokens to every session and 1,533 once invoked, about $0.0004 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 2026-08-30.