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/meringlab/string-mcp/string-databasenpx skills add meringlab/string-mcp --skill string-databasegit clone --depth 1 https://github.com/meringlab/string-mcpWhat 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 | $0.00060 | $0.01177 |
| Opus 5 | $0.00030 | $0.00589 |
| Sonnet 5 | $0.00012 | $0.00235 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
string-database 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STRING Database
Use the STRING MCP tools as the source of truth for protein interaction, network, enrichment, annotation, evidence, species, and homolog questions.
Grounding Rules
- Use STRING tool output for factual claims about interactions, functions, pathways, enrichment, annotations, homologs, and species availability.
- If no species is provided, use human, NCBI taxon ID
9606. - Do not guess, assemble, or derive STRING links or image URLs. Only show exact links and image URLs returned by tools.
- If a requested claim is not supported by the current tool output in context, retrieve the relevant STRING data with parameters specific to the new claim.
- If identifiers are ambiguous, resolve them with
string_resolve_proteinsbefore analysis. - If the input is an amino acid sequence rather than an identifier, use
string_sequence_search. - If a species name or taxon is uncertain, use
string_query_species. - If a requested STRING capability is unavailable through the tools, use
string_helpwhen a matching help topic exists. - Avoid repeating the same tool call with identical inputs unless the user asks to retry.
Tool Selection
Use string_resolve_proteins to map gene symbols, UniProt IDs, or other protein identifiers to STRING metadata.
Use string_interactions_query_set to retrieve interactions among the submitted proteins. For binding, complex, co-complex, or physical-interaction questions, set network_type to physical.
Use string_all_interaction_partners when the user asks what a protein interacts with, or asks for partners beyond the submitted set.
Use string_visual_network when the user asks for a network image. Use the same protein, species, score, extension, and network-type parameters as related network calls.
Use string_network_link when the user asks for an interactive STRING network page.
Use string_network_clustering when the user asks for network clusters, modules, or grouped subnetworks.
Use string_interaction_evidence when the user asks for STRING evidence pages for specific protein pairs. If the user asks whether an interaction is supported, first verify with string_interactions_query_set.
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.
- yesterday First seen · 77 lines · 60 tokens per session scan A 432fb31f95fb
string-database is a skill published in the GitHub repository meringlab/string-mcp (5 stars, last pushed 12d ago), licensed MIT. It adds 60 tokens to every session and 1,177 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…