shelx

shelx is a skill for Claude Code, Codex from stge4code/shelx-mcp. It costs 42 tokens per session (979 once invoked), scanned B, original, MIT.

A chat-based interface for SHELX, a set of programs used to solve and refine crystal structures from crystallographic data. It works with files such as .ins instruction files and .hkl reflection data.

In plain words
What is it for?
Use it to validate .ins files, look up SHELX instructions, solve or refine structures, run supported SHELX programs, and analyze refinement results.
Why use it?
It gives researchers one workflow for checking input files, consulting instructions, running structure solution or refinement, and examining results. This avoids having to remember each SHELX command and format.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

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.

agentmods
npx agentmods add skills/stge4code/shelx-mcp/shelx
Any agent
npx skills add stge4code/shelx-mcp --skill shelx
Clone the repo
git clone --depth 1 https://github.com/stge4code/shelx-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for shelx

README.md
[![agentmods](https://agentmods.dev/badge/skills/stge4code/shelx-mcp/shelx.svg)](https://agentmods.dev/skills/stge4code/shelx-mcp/shelx)
Your own site
<a href="https://agentmods.dev/skills/stge4code/shelx-mcp/shelx"><img src="https://agentmods.dev/badge/skills/stge4code/shelx-mcp/shelx.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 979 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.00979
Opus 5 $0.00021 $0.00490
Sonnet 5 $0.00008 $0.00196
Haiku 4.5 $0.00004 $0.00098

Measured 6d ago against content hash 8eb562cc7034, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

shelx scanned grade B 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 6d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- Only the allowlisted programs can run; never try to execute arbitrary commands.
skills/shelx/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SHELX crystallography workflow

This skill drives the shelx-mcp MCP server, which wraps the SHELX console programs (SHELXL, SHELXS, SHELXT, SHELXC/D/E, CIFTAB). Use it whenever the user has crystallographic data (.ins / .hkl) or wants to build/run a SHELX job.

Tools available

  • list_commands / command_help(name) / search_commands(query) — the bundled, offline SHELXL refinement instruction reference.
  • list_solution_keywords(program) / solution_help(program, keyword) — the bundled SHELXS / SHELXD / SHELXD-MM .ins cards (e.g. TREF, FIND, SHEL, DSUL), SHELXT command-line switches (e.g. -a, -d, -L), SHELXC stdin keywords (e.g. SAD, CELL, SPAG) and SHELXE command-line options (e.g. -aN, -h). Programs: shelxs, shelxd, shelxd_mm, shelxt, shelxc, shelxe.
  • validate_ins(ins) — check the required header cards (TITL, CELL, ZERR, LATT, SYMM, SFAC, UNIT, HKLF, END).
  • solve(ins, hkl, program="shelxs") — structure solution (use shelxt for dual-space/intrinsic phasing).
  • refine(ins, hkl, program="shelxl") — least-squares refinement.
  • run_shelx(program, ins, hkl, ...) — raw runner for any allowed program.
  • analyze_results(lst, res) — extract R1, wR2, GooF (S), max shift/esd, atom count and warnings from SHELXL output.
  • analyze_solution(lxt, res) — extract R1, alpha, space group, Flack x, CC and atom count from SHELXT output (name.lxt + name_a.res).
  • shelx_info() — report the configured SHELX directory and available programs.
  1. Orient. If the user names an unfamiliar instruction, look it up before writing it:
    • refinement card: command_help("NAME") (or search_commands for a keyword).
    • solution keyword: list_solution_keywords("shelxs") then solution_help("shelxs", "TREF").
  2. Build / receive the model. Get or generate the .ins text, then run validate_ins and fix any missing header cards.
  3. Solve (if starting from raw data): solve(ins, hkl). Prefer program="shelxt" for small molecules (it usually gives a more complete solution than SHELXS); read the returned .lxt / name_a.res and check the outcome with analyze_solution(lxt=..., res=...) (low R1, sensible space group, Flack x near 0 for the correct absolute structure).
  4. Refine: refine(ins, hkl). Iterate — tighten restraints, add ANIS, adjust WGHT — re-running each time.
  5. Check the outcome: analyze_results(lst=..., res=...) and react to warnings (e.g. "missed symmetry", non-positive-definite atoms, high R1).

Read the full file on GitHub · 61 lines

Changes

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.

  1. 6d ago First seen · 61 lines · 42 tokens per session scan B 8eb562cc7034

Subscribe to this mod's changes

shelx is a skill published in the GitHub repository stge4code/shelx-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 979 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens