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 skills add BioSymphony/structure-factory --skill biosymphony-structure-factorygit clone --depth 1 https://github.com/BioSymphony/structure-factoryWrote 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/biosymphony/structure-factory/biosymphony-structure-factory)<a href="https://agentmods.dev/skills/biosymphony/structure-factory/biosymphony-structure-factory"><img src="https://agentmods.dev/badge/skills/biosymphony/structure-factory/biosymphony-structure-factory/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.
<a href="https://agentmods.dev/skills/biosymphony/structure-factory/biosymphony-structure-factory"><img src="https://agentmods.dev/badge/skills/biosymphony/structure-factory/biosymphony-structure-factory.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00043 | $0.01875 |
| Opus 5.5 | $0.00017 | $0.00750 |
| Sonnet 5.5 | $0.00009 | $0.00375 |
| Haiku 4.5 | $0.00004 | $0.00187 |
Grade A, and why
biosymphony-structure-factory 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 19d 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BioSymphony Structure Factory
Use the tool knowledge base to select methods for a target, accession, or screening request. Call configured tools through the CLI or installed platform skills, connect stage outputs, and compare structures and candidate rankings.
Start with the requested outcome
Read references/README.md, references/AGENTS.md, and
references/NON_CLAIMS.md, then select the work:
| Request | Deliverable |
|---|---|
| Choose tools | Methods, input/output requirements, source references, and runtime options |
| Call and chain tools | Configured adapters, stage dependencies, and checked downstream inputs |
| Plan a campaign | Target definition, selected tools, and stage contracts |
| Demonstrate a workflow | Public or synthetic inputs with a labeled example report |
| Prepare GPU execution | Provider profile, resource limits, launch request, and validation commands |
| Review results | Candidate ranking or structure report with source files and validation results |
| Run a campaign | Authorized execution followed by artifact verification and resource cleanup |
For ambiguous inputs, tools, or spending limits, use
references/docs/intake-interview.md to resolve the missing decisions.
For a first campaign, use references/docs/quickstart-tour.md; find command
options in references/docs/cli-reference.md.
Bundled references keep links to included files local. Links to repository files outside this compact bundle point to the canonical public GitHub tree. Use the selected repository checkout for CLI commands and runtime files.
Read the references for your task
| Task | References |
|---|---|
| Find methods | Full tool index, software registry, references/docs/tool-and-skill-radar.md |
| Select tools and compute | references/docs/tooling-and-licensing.md, references/docs/compute-backends.md |
| Plan binder comparisons | references/docs/binder-lane-round.md, references/docs/binder-study-decision-loop.md |
| Choose measured controls | references/docs/binder-controls.md |
| Qualify candidate filters | Binder filtering, filter qualification contract |
| Compare pH contributions | pH comparison, ProtonPottsMPNN |
| Review design inputs | GuideFlip measurements, glycan context |
| Select property-aligned sequence design | MoMPNN |
| Compare protein-ligand scores | Affinity scoring card: input modality, endpoint, scale, and pose controls |
| Plan Slurm prediction phases | BioNeMo pipeline card: MSA handoffs, backend policy, and phase receipts |
| Use BindCraft2 | references/tools/bindcraft2.md: presets, resource limits, output tables, score scales, and license |
| Qualify Anthropic acceleration | references/tools/anthropic-optimization-kits.md: stock revision, runtime isolation, activation, and matched comparisons |
| Score or render predictions | references/docs/confidence-sidecars.md |
| Prepare provider execution | references/docs/preflight-checklist.md, references/docs/operational-gotchas.md; add references/docs/runpod-stack.md for RunPod |
| Coordinate workers | references/docs/agentic-biology-harness.md, references/docs/linear-orchestration.md |
| Define run completion checks | references/docs/no-false-success-hardening.md, references/docs/agent-run-learnings.md |
| Verify prediction artifacts | Prediction handoff contract |
What ships with it
60 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.
- agents/openai.yaml 205 B
- references/AGENTS.md 6.4 KB
- references/binder-execution-adapters.json 54 KB
- references/binder-lane-capability-ledger.json 17 KB
- references/docs/agent-boundaries.md 1.2 KB
- references/docs/agent-recipes.md 5.5 KB
- references/docs/agent-run-learnings.md 4.4 KB
- references/docs/agentic-biology-harness.md 7.1 KB
- references/docs/ai-design-runtime-readiness.md 14 KB
- references/docs/architecture.md 3.3 KB
- references/docs/assets/agent-lanes.svg 5.4 KB
- references/docs/assets/newcomer-paths.svg 4.5 KB
- references/docs/assets/README.md 2.3 KB
- references/docs/assets/structure-factory-banner.png 1523 KB
- references/docs/assets/structure-factory-loop.svg 3.9 KB
- references/docs/assets/structure-factory-social-preview.jpg 495 KB
- references/docs/assets/system-context.svg 2.5 KB
- references/docs/assets/workflow-ladder.svg 2.5 KB
- references/docs/binder-comparison-contract.md 4.9 KB
- references/docs/binder-controls.md 4.7 KB
- references/docs/binder-lane-round.md 32 KB
- references/docs/binder-study-decision-loop.md 9.0 KB
- references/docs/capabilities.md 9.7 KB
- references/docs/cli-reference.md 11 KB
- references/docs/compute-backends.md 9.3 KB
- references/docs/confidence-sidecars.md 3.6 KB
- references/docs/faq.md 8.0 KB
- references/docs/genie3-boltz-demo-ideas.md 5.2 KB
- references/docs/glossary.md 7.0 KB
- references/docs/install-sidecar.md 1.8 KB
- references/docs/intake-interview.md 3.7 KB
- references/docs/linear-orchestration.md 9.4 KB
- references/docs/no-false-success-hardening.md 9.2 KB
- references/docs/operational-gotchas.md 32 KB
- references/docs/prediction-handoff-contract.md 3.8 KB
- references/docs/preflight-checklist.md 16 KB
- references/docs/privacy-and-security-model.md 2.6 KB
- references/docs/public-export-shape.md 4.2 KB
- references/docs/public-repo-and-private-image-policy.md 11 KB
- references/docs/public-switch-checklist.md 3.0 KB
- references/docs/quickstart-tour.md 5.9 KB
- references/docs/release-process.md 1.3 KB
- references/docs/reproducibility-checks.md 1.5 KB
- references/docs/result-boundaries.md 4.8 KB
- references/docs/runpod-stack.md 11 KB
- references/docs/scoring-invariants.md 2.5 KB
- references/docs/screening-superpowers.md 10 KB
- references/docs/sidecar-architecture.md 1.8 KB
- references/docs/skill-install.md 1.5 KB
- references/docs/standalone-agent-workflow.md 2.4 KB
- references/docs/tool-and-skill-radar.md 13 KB
- references/docs/tooling-and-licensing.md 14 KB
- references/docs/use-cases.md 15 KB
- references/docs/workflow-map.md 9.5 KB
- references/examples/binder-controls-synthetic/control-observations.jsonl 1.7 KB
- references/examples/binder-controls-synthetic/control-panel.json 1.8 KB
- references/examples/binder-controls-synthetic/README.md 713 B
- references/examples/pd-l1-binder-design-public/binder-round-request.json 6.0 KB
- references/examples/pd-l1-binder-design-public/campaign-manifest.json 1.9 KB
- references/examples/pd-l1-binder-design-public/candidate-ranking.example.json 2.3 KB
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.
- 19d ago Changed · +3 lines 2859f835fd74
- 25d ago Changed · +7 lines e730d86e1bca
- 1mo ago Changed · +9 lines · -2 tokens per session 7a77aab370cb
- 1mo ago Changed · +8 lines · -2 tokens per session 92e6cfa84c19
- 1mo ago Changed · +1 lines 87a9e95be95d
- 1mo ago First seen · 112 lines · 47 tokens per session scan A 3f6d5b993906
biosymphony-structure-factory is a skill published in the GitHub repository BioSymphony/structure-factory (13 stars, last pushed 14d ago), licensed MIT. It adds 43 tokens to every session and 1,875 once invoked, about $0.0002 per session on Opus 5.5. 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
dna-methylation
DNA methylation analysis — array (450K/EPIC), bisulfite-seq, DMP/DMR detection, clocks, deconvolution, and EWAS.
statistical-modeling
Statistical modeling and machine learning for biomarker discovery, survival analysis, classification, regression, and model interpretation.
chromatin-regulation
Chromatin regulation analysis from called peaks and count matrices — differential binding, signal summarisation, peak annotation, and scATAC-seq.
genomic-variants
Analysis of called genomic variants — filtering, annotation, GWAS, and population-genetics summaries from VCF and PLINK-format data.
bulk-transcriptomics
Bulk RNA-seq and microarray differential expression analysis including method selection, batch correction, and complex experimental designs.
spatial-omics
Spatial transcriptomics and spatial proteomics analysis covering technology-specific workflows, spatial statistics, deconvolution, and niche analysis.