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/google-deepmind/science-skills/pdb_databasenpx skills add google-deepmind/science-skills --skill pdb_databasegit clone --depth 1 https://github.com/google-deepmind/science-skillsWhat 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 | $0.00061 | $0.02305 |
| Opus 5 | $0.00030 | $0.01153 |
| Sonnet 5 | $0.00012 | $0.00461 |
| Haiku 4.5 | $0.00006 | $0.00231 |
Grade A, and why
pdb-database scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl`, `urllib`, raw HTTP requests, or any other method to access PDB APIs. How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RCSB Protein Data Bank skill
Prerequisites
uv: Read theuvskill and follow its Setup instructions to ensureuvis installed and on PATH.- User Notification: If .licenses/pdb_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.rcsb.org/pages/usage-policy, then (2) create the file recording the notification text and timestamp.
Core Rules
- Always prefer to use the provided scripts. Only as a last resort use
curl,urllib, raw HTTP requests, or any other method to access PDB APIs. The scripts automatically enforce required rate limits. - Always redirect output to a file. Parse output with e.g.
jq,grep, or a short Python snippet. Do NOT print large API responses to stdout to avoid truncation. - Notification: If this skill is used, ensure this is mentioned in the output.
- Explain your queries On completing a task that used PDB JSON/GraphQL queries, explain in clear language what your query did so the user can correct any bad assumptions.
Attribute-based search workflow
-
Fetch the relevant schema to discover searchable attribute names. For structure attributes:
uv run scripts/fetch_schema.py --api search_structure --output schema_structure.txtFor chemical attributes:uv run scripts/fetch_schema.py --api search_chemical --output schema_chemical.txt -
Grep the schema to find relevant attributes. Grep one keyword at a time and examine many lines — there are lots of similar attributes and you must choose the best match for the user's intent.
-
Compose and run a JSON search query using the discovered attributes:
uv run scripts/search_pdb.py --query '<JSON>' --return_type <RETURN_TYPE> --output results.jsonPass the--count_onlyflag to get just the number of matching entries.
For step 2: some basic PDB concepts (helpful for attribute choice)
What ships with it
5 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.
- yesterday First seen · 170 lines · 61 tokens per session scan A 9d5f96f75127
pdb-database is a skill published in the GitHub repository google-deepmind/science-skills (2,794 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 2,305 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (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
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…