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/openscientist-io/openscientist/phenix-tools-referencenpx skills add openscientist-io/openscientist --skill phenix-tools-referencegit clone --depth 1 https://github.com/openscientist-io/openscientistWrote 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/openscientist-io/openscientist/phenix-tools-reference)<a href="https://agentmods.dev/skills/openscientist-io/openscientist/phenix-tools-reference"><img src="https://agentmods.dev/badge/skills/openscientist-io/openscientist/phenix-tools-reference.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.02238 |
| Opus 5 | $0.00008 | $0.01119 |
| Sonnet 5 | $0.00003 | $0.00448 |
| Haiku 4.5 | $0.00002 | $0.00224 |
Grade A, and why
phenix-tools-reference 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 4d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phenix Tools Reference
If Phenix is available, prefer run_phenix_tool over execute_code for structural biology tasks like validation, superposition, refinement, and map analysis. Phenix is the gold standard for these tasks.
Call run_phenix_tool(tool_name="phenix.<command>", input_files=["file.pdb"], description="..."). This reference lists the most useful commands grouped by task. Most commands accept PDB or mmCIF files, but some take map files, reflection data, sequences, or other formats — check each tool's --help if you are unsure.
Validation and Quality Assessment
| Command | Purpose |
|---|---|
phenix.molprobity |
Comprehensive validation: Ramachandran, rotamers, clashes, C-beta deviations; the single best overall quality check |
phenix.clashscore |
All-atom steric clash analysis |
phenix.ramalyze |
Ramachandran backbone analysis |
phenix.rotalyze |
Side-chain rotamer analysis |
phenix.cablam |
C-alpha based backbone validation |
phenix.cbetadev |
C-beta deviation analysis |
phenix.omegalyze |
Cis/trans peptide bond validation |
phenix.model_vs_data |
Model versus diffraction data statistics |
phenix.model_statistics |
Summary geometry statistics for a model |
phenix.emringer |
Map-model validation for cryo-EM structures |
phenix.validation_cryoem |
Comprehensive cryo-EM validation |
phenix.undowser_validation |
Check waters for clashes and poor contacts |
phenix.clashscore2 |
Updated all-atom clash score (prefer over clashscore when available; slightly different scoring) |
phenix.undowser2_validation |
Updated water validation (same relationship to undowser_validation as above) |
phenix.holton_geometry_validation |
Holton-method geometry validation — complementary signal to molprobity; useful for second-opinion checks |
Example: Full validation
run_phenix_tool(
tool_name="phenix.molprobity",
input_files=["structure.pdb"],
description="Comprehensive structure quality check",
)
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.
- 4d ago First seen · 195 lines · 15 tokens per session scan A 5015ecb6cd5d
phenix-tools-reference is a skill published in the GitHub repository openscientist-io/openscientist (49 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 2,238 once invoked, about $0.0001 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
site-config-creation
Create or update the [site] section of stencila.toml for published Stencila sites. Use when asked to configure site domain, title, author, logo, icons, labels, descriptions, socials, featured content, navigation, routes, access, layout presets and regions, glide, search, formats, reviews, uploads, remotes, actions…
huawei-cloud-swr-enterprise-instance
Huawei Cloud SWR enterprise instance management skill using hcloud CLI. Use this skill when the user wants to: (1) manage SWR enterprise instances - create/list/show/delete/update configuration, (2) manage instance namespaces - create/list/show/update/delete with security scanning settings, (3) manage instance…
domain-modeling
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
system-building-as-meaning-making
Use when a system is carrying meaning beyond utility. Owns meaning-layer interpretation only.
isdomainok-domain-naming
Generate, screen, and rank project, product, company, app, and brand names by checking real domain availability with IsDomainOK. Use when a user asks for naming ideas, available domains, brandable names, TLD comparisons, or wants to avoid suggestions whose domains are already registered or over budget.
deploy
Deploy the crosbynews Worker to Cloudflare and verify it's live. Syntax-checks every file under src/, surfaces branch/working-tree state, runs npx wrangler deploy, then curls the live site. Use when asked to deploy, ship, or push the Worker live.