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 wzyn20051216/matlab-agent-skills --skill matlab-runnergit clone --depth 1 https://github.com/wzyn20051216/matlab-agent-skillsWrote 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/wzyn20051216/matlab-agent-skills/matlab-runner)<a href="https://agentmods.dev/skills/wzyn20051216/matlab-agent-skills/matlab-runner"><img src="https://agentmods.dev/badge/skills/wzyn20051216/matlab-agent-skills/matlab-runner/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/wzyn20051216/matlab-agent-skills/matlab-runner"><img src="https://agentmods.dev/badge/skills/wzyn20051216/matlab-agent-skills/matlab-runner.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 | $0.00057 | $0.02215 |
| Opus 5.5 | $0.00023 | $0.00886 |
| Sonnet 5.5 | $0.00011 | $0.00443 |
| Haiku 4.5 | $0.00006 | $0.00221 |
Grade A, and why
matlab-runner 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MATLAB Runner
Use this skill to execute MATLAB work safely and repeatably through the official MATLAB MCP server, preferably in auto mode, and only use terminal batch workflows when the user explicitly asks for them. It is the foundation skill for all other MATLAB skills.
References — load on demand
This file carries the workflow. The tables below are not loaded unless the task actually reaches them, because each is a few hundred tokens of detail that costs context on every run and goes stale on every MATLAB release.
| Load this | when |
|---|---|
references/toolbox-feature-map.md |
resolving a product name to a licence feature |
references/mcp-readiness-ladder.md |
about to claim MCP is ready, or MCP failed |
references/acceptance-levels.md |
about to write an acceptance report |
references/failure-classes.md |
a run failed and you are deciding whether to retry |
Execution Rules
- Prefer the official MATLAB MCP auto mode for MATLAB work on this machine.
- Do not silently fall back to
matlab -batchwhen MCP is expected. - Capture logs, version info, working directory, and artifact paths where applicable.
- Run from a project root, not from a random temporary folder, unless isolation is required.
- Put generated files under
artifacts/or a user-specified output folder. - Keep scripts deterministic: seed random generators and record data sources.
Precheck Before A Long Run
Phase 3B.1 shipped five scripts and none ran on the first attempt; most of those failures were detectable in seconds. Run the cheap checks first, in this order:
r = mas_precheck('function', 'boost_params'); % exists?
r = mas_precheck('struct', cfg, {'Vin','L','C'}); % fields present?
r = mas_precheck('numeric', x, struct('finite',true)); % NaN/Inf?
r = mas_precheck('index', mask, numel(target)); % mask length
r = mas_precheck('toolbox', 'Control System Toolbox'); % product vs feature
r = mas_precheck('model', 'matlab/boost/models/boost_avg.slx');
What ships with it
10 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.
- references/acceptance-levels.md 2.9 KB
- references/failure-classes.md 2.5 KB
- references/mcp-readiness-ladder.md 4.4 KB
- references/toolbox-feature-map.md 1.1 KB
- scripts/mas_dep_probe.m 11 KB
- scripts/mas_precheck.m 7.5 KB
- scripts/mas_product_map.m 6.2 KB
- scripts/mas_toolbox_map.m 2.8 KB
- tests/test_dep_probe.m 6.2 KB
- tests/test_precheck.m 3.6 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.
- 4d ago Changed · +105 lines · -4 tokens per session 380bb682188f
- 1mo ago First seen · 101 lines · 61 tokens per session scan A 5e316f0b77a3
matlab-runner is a skill published in the GitHub repository wzyn20051216/matlab-agent-skills (27 stars, last pushed 5d ago), licensed MIT. It adds 57 tokens to every session and 2,215 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 2026-08-30.
Other skills, from other repositories
manim-video
Create mathematical, geometric and scientific videos with Manim Community in Python. Use when animating equations, graphs, transformations or educational explanations; distinguish Manim Community from ManimGL and deliver a rendered, inspected video.
ml-experiment-tracker
Plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to standardize tracking-ready experiment definitions.
nature-statistics
A guide for checking or writing how statistical analyses are reported in scientific papers submitted to Nature or similar high-impact journals.
nature-paper-trans
A workflow for translating selected pages or a complete English research-paper PDF into a simplified-Chinese, image-based PDF. bioRxiv is not mentioned in the provided details; the workflow applies to research-paper PDFs generally.
nature-citation
A citation-writing workflow for adding references from selected Nature Portfolio, AAAS Science, and Cell Press journals to manuscript text. It breaks long passages into smaller claims and matches them with eligible papers.
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.