Feynman is an open-source AI research agent that helps users investigate topics with language models. It supports local model providers and hosted model authentication through its setup process. The catalogue contains skills, agents, and instructions that extend Feynman’s workflows.
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 companion-inc/feynman --skill boltzgit clone --depth 1 https://github.com/companion-inc/feynmanWrote 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/companion-inc/feynman/boltz)<a href="https://agentmods.dev/skills/companion-inc/feynman/boltz"><img src="https://agentmods.dev/badge/skills/companion-inc/feynman/boltz/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/companion-inc/feynman/boltz"><img src="https://agentmods.dev/badge/skills/companion-inc/feynman/boltz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00047 | $0.00249 |
| Opus 5 | $0.00023 | $0.00125 |
| Sonnet 5 | $0.00009 | $0.00050 |
| Haiku 4.5 | $0.00005 | $0.00025 |
Grade A, and why
boltz 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 10d 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.
What it actually says
Boltz
Use this skill when the active research run needs Boltz-style biomolecular prediction.
Workflow:
- Normalize inputs into explicit entities: protein chains, nucleic-acid chains, ligands, covalent links, templates, constraints, and seeds.
- Verify the available execution route from Feynman Settings, notebook runtimes, managed endpoints, Modal, SSH, or local installs before claiming the model can run.
- Run only from a recorded input manifest. Preserve exact sequences, ligand identifiers, model parameters, seed, hardware, package version, and command.
- Save structures, confidence outputs, logs, and rendered previews as Feynman artifacts.
- Interpret the output as a hypothesis: separate high-confidence local folds from weak interfaces, ligand poses, flexible regions, and unsupported biological claims.
Do not treat a single attractive structure as proof. Add verification checks against source literature, known structures, or orthogonal experiments when the result drives a decision.
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.
- 10d ago First seen · 19 lines · 47 tokens per session scan A a116111f28ac
boltz is a skill published in the GitHub repository companion-inc/feynman (8,870 stars, last pushed 14d ago), licensed MIT. It adds 47 tokens to every session and 249 once invoked, about $0.0002 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.
Other skills, from other repositories
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.