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 cyanheads/calculator-mcp-server --skill calculator-guidegit clone --depth 1 https://github.com/cyanheads/calculator-mcp-serverWrote 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/cyanheads/calculator-mcp-server/calculator-guide)<a href="https://agentmods.dev/skills/cyanheads/calculator-mcp-server/calculator-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/calculator-mcp-server/calculator-guide/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/cyanheads/calculator-mcp-server/calculator-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/calculator-mcp-server/calculator-guide.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 | $0.00083 | $0.03127 |
| Opus 5.5 | $0.00033 | $0.01251 |
| Sonnet 5.5 | $0.00017 | $0.00625 |
| Haiku 4.5 | $0.00008 | $0.00313 |
Grade A, and why
calculator-guide 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Reach for calculate before stating any number you did not copy from a source. It has none of these:
- Symbolic integration:
integrateis numeric. - A nonlinear equation solver. Tabulate to bracket a root instead:
map(0:0.1:1, f(x) = x - cos(x))changes sign between 0.7 (-0.06484218728448854) and 0.8 (0.10329329065283444). - Probability distribution functions:
normcdf(1.96)anderfinv(0.95)fail withparse_failed. The normal CDF is0.5 * (1 + erf(1.96 / sqrt(2)))→0.9750021048517796; there is no inverse. - Finance functions: write the closed form.
300000 * (0.065/12) / (1 - (1 + 0.065/12)^(-360))→1896.2040704788958. - Currency (
5 USD to EURfails withparse_failed), business-day or holiday calendars (see Dates and deadlines), and time of day. - These units, which fail with
parse_failed:kcal,cal,au,parsec,rpm,nauticalmile,ukgallon,tbsp. Writetablespoon:1 tablespoon to mL→15.000000000000002 mL.
Physical constants evaluate as units: speedOfLight → 299792458 m / s, elementaryCharge → 1.602176634e-19 C, and planckConstant, avogadro, gravitationConstant.
Choosing numericType
| Question | numericType | Measured |
|---|---|---|
| An exact integer: a count, binomial, factorial, power, or remainder | "Fraction", then drop the /1 |
nCr(100, 50) → 100891344545564193334812497256/1. Under "BigNumber" the same digits print as 1.00891344545564193334812497256e+29 |
| An exact probability or ratio | "Fraction" |
3744 / combinations(52, 5) → 6/4165. round(x, n) fails under it with fraction_unsupported; for the decimal, rerun under "BigNumber" with precision: 10: 6/4165 → 0.00144057623 |
| Money: payments, interest, totals | "number", rounded with round(x, 2) |
precision counts significant digits, not decimal places: 382633.47 with precision: 4 → 382600. Under "Fraction" the 360-period payment above is an exact fraction thousands of digits long |
| A value past float range, or more digits than a float holds | "BigNumber" with precision |
1 - permutations(365, 23) / 365^23 with precision: 10 → 0.5072972343 |
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 · 98 lines · 83 tokens per session scan A 065c483ffd73
calculator-guide is a skill published in the GitHub repository cyanheads/calculator-mcp-server (3 stars, last pushed 5d ago), licensed Apache-2.0. It adds 83 tokens to every session and 3,127 once invoked, about $0.0003 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 2026-11-13.
calculator-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| calculator-guidecyanheads/calculator-mcp-server | Skill | 3 | 5d ago | Apache-2.0 | A | 83 | Claude Code |
| pubchem-guidecyanheads/pubchem-mcp-server | Skill | 13 | 4d ago | Apache-2.0 | A | 87 | Claude Code |
| brapi-guidecyanheads/brapi-mcp-server | Skill | 4 | 4d ago | Apache-2.0 | A | 43 | Claude Code |
| codecalcThe-40-Thieves/codecalc | Skill | 5 | today | Apache-2.0 | A | 52 | Claude Code, Codex |
| axiom-mathtufantunc/axiom-advanced-math-mcp | Skill | 3 | yesterday | GPL-3.0 | A | 74 | Claude Code, Codex |
| paper-searchopenags/paper-search-mcp | Skill | 3.1k | 1mo ago | MIT | A | 62 | Claude Code, Codex |
| quantum-amplitude-estimationxi-zhao/OpenQuantum | Skill | 72 | 2d ago | MIT | A | 63 | Claude Code, Codex |