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 instructions/biosymphony/structure-factory/agents-mdgit clone --depth 1 https://github.com/BioSymphony/structure-factoryWhat 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 | $0.01610 | $0.01610 |
| Opus 5 | $0.00805 | $0.00805 |
| Sonnet 5 | $0.00322 | $0.00322 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
structure-factory AGENTS.md 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BioSymphony Structure Factory Agent Guide
Workspace for long-horizon structural biology missions, built for agents that drive multi-agent harnesses (Symphony with Linear, Claude Code with Linear, Codex, /goal, GitHub Issues, Notion, or any tracker).
Mission
Help a user and their agents take a structural biology goal (for example, "design binders for PD-L1," "atlas every active-state GPCR in the PDB," "map this public EMDB/PDB structure," or "fan out a screening campaign across cloud") and run it to reviewable completion across local and cloud compute.
The repo ships:
- portable agent instructions for any agent runtime
- campaign manifests, stage contracts, and provider profiles for RunPod, AWS, Modal, Lambda, neocloud, HPC, and local
- target-window files, generation, cofold, scoring, render, and screening lanes
- tracker-neutral task packs that import cleanly into Linear, GitHub Issues, Notion, or any queue
- validators, audit gates, capability catalog, and a dependency-free
bsfCLI
Ownership boundary: raw cryo-EM movie intake, EMPIAR subset execution, RELION or CryoSPARC reconstruction, and map-to-model build execution belong to BioSymphony CryoCore. This repo keeps public metadata, handoff gates, downstream structure-mapping contracts, validation plans, and reviewable summaries.
How To Drive A Mission
When the orchestrator hands you work, the loop is:
goal
-> bsf catalog . # what is available
-> bsf scaffold-campaign <runtime>/<id> ... # target, lanes, run boundaries
-> bsf validate <runtime>/<id> # campaign and stage contract sound
-> bsf issue-dry-run # split into tracker work
-> orchestrate workers or launch provider # Symphony, Linear, Codex, others
-> verify artifacts and sign closeout
Fan out across multiple workers when the work exceeds one agent turn. Task packs define owned paths, dependencies, validation commands, and outcome schemas so workers can run in parallel without colliding.
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 · 115 lines · 1,610 tokens per session scan A 0c9b0500ad8d
structure-factory AGENTS.md is an instructions file published in the GitHub repository BioSymphony/structure-factory (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,610 tokens to every session, about $0.0080 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 instructions, from other repositories
precision-medicine-mcp CLAUDE.md
Instructions for lynnlangit/precision-medicine-mcp, covering claude.md — project context for claude code, git workflow, session management, what this project is and repository structure.
asb-skill-collections CLAUDE.md
Instructions for HolobiomicsLab/asb-skill-collections, covering claude.md — asb metabolomics skills, install (claude code plugin) and use.
cryocore AGENTS.md
Instructions for BioSymphony/cryocore, covering biosymphony cryocore agent guide, operating rules, ownership boundary, dev commands and key patterns and conventions.
asb-skill-collections copilot-instructions.md
Instructions for HolobiomicsLab/asb-skill-collections: This repository publishes the ASB Metabolomics Skill Collection (collections/metabolomics/v2/): 5,859 evidence-grounded skills over 909 software tools for computational LC-MS/MS metabolomics, each derived from a peer-reviewed method paper.
bioinformatics-agent-skills AGENTS.md
Instructions for YuliaNuzhnenko/bioinformatics-agent-skills, covering agent integration & specification guide 🤖, 📌 supported agent host architectures, 🧪 skill frontmatter specification and 🔒 security & sandboxing.
bioinformatics-agent-skills CLAUDE.md
Instructions for YuliaNuzhnenko/bioinformatics-agent-skills, covering claude code project guidelines, project overview, development & validation commands and skill conventions.