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/danielsimonjr/math-mcp/mathnpx skills add danielsimonjr/math-mcp --skill mathgit clone --depth 1 https://github.com/danielsimonjr/math-mcpWrote 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/danielsimonjr/math-mcp/math)<a href="https://agentmods.dev/skills/danielsimonjr/math-mcp/math"><img src="https://agentmods.dev/badge/skills/danielsimonjr/math-mcp/math.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 | $0.00205 | $0.02068 |
| Opus 5 | $0.00102 | $0.01034 |
| Sonnet 5 | $0.00041 | $0.00414 |
| Haiku 4.5 | $0.00020 | $0.00207 |
Grade A, and why
math 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Math
A judgment layer over the math-mcp server's 7 pure computation tools — expression evaluation, calculus, equation solving, simplification, matrix algebra, statistics, and unit conversion. This skill adds no tools of its own: every action below is one of the server's existing MCP tools. Its job is to steer you toward calling the tool instead of computing in your head, help you pick evaluate vs. a specialized tool, sequence multi-step workflows correctly, and flag the mathjs-compatible-syntax gotchas that produce wrong or confusing results. The compute engine is MathTS (@danielsimonjr/mathts-*), which keeps mathjs-compatible input syntax.
Skill root: this skill ships inside the math-mcp plugin (repo danielsimonjr/math-mcp, skills/math/). Slash trigger: /math.
The offload rule
Non-trivial computation goes to math-mcp, not mental math. Self-computed arithmetic is error-prone — the moment a calculation is worth getting exactly right, call the tool instead of estimating or working it out by hand. This is the same principle as "prefer the MCP over ad-hoc work" from the windows skill, applied to numbers instead of the desktop.
Where the line sits:
- Trivial inline arithmetic —
2+2, a single-digit product, a fact you already know cold — may be answered directly. - Everything else goes to the tool: exact/CAS results, any derivative or calculus step, any matrix operation beyond a hand-checkable 2×2, statistics over a real dataset, unit conversions, and any figure the user will actually rely on (a report number, a formula check, an engineering value). If it's worth being right about, it's worth calling the tool.
Tool selection: evaluate vs. the 6 specialized tools
The overlap between evaluate and the specialized tools is intentional. evaluate is the MathTS workhorse (mathjs-compatible syntax) — it can inline derivative(...), det(...), and most of what the specialized tools do, all in one expression. Use evaluate for a one-off general expression or when combining several operations in a single call (pass a scope object to supply variables). Reach for a specialized tool when you want its narrower, validated result shape or its specific operation directly — e.g. a clean symbolic derivative string from derivative, or an enum-constrained matrix op from matrix_operations.
What ships with it
1 file 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.
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 · 92 lines · 205 tokens per session scan A 8c6386647af2
math is a skill published in the GitHub repository danielsimonjr/math-mcp (0 stars, last pushed 2d ago), licensed ISC. It adds 205 tokens to every session and 2,068 once invoked, about $0.0010 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 2026-09-01.
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…
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…
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.
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.
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.
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…