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/exchange-rates-mcp-server --skill exchange-rates-guidegit clone --depth 1 https://github.com/cyanheads/exchange-rates-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/exchange-rates-mcp-server/exchange-rates-guide)<a href="https://agentmods.dev/skills/cyanheads/exchange-rates-mcp-server/exchange-rates-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/exchange-rates-mcp-server/exchange-rates-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/exchange-rates-mcp-server/exchange-rates-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/exchange-rates-mcp-server/exchange-rates-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 | $0.00057 | $0.00985 |
| Opus 5.5 | $0.00023 | $0.00394 |
| Sonnet 5.5 | $0.00011 | $0.00197 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
exchange-rates-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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Use this keyless server for Frankfurter v1 daily reference-rate analysis. For a single converted amount use fx_convert_currency; for a rate use fx_get_rate; for a latest snapshot use fx_get_rates or fx://rates/latest/{base}. These rates do not establish an executable trade price or a required tax or accounting method.
Identifiers
Resolve ambiguous currency names through fx_list_currencies. Its retired-currency discovery adds historical codes; fx://currencies remains current-only. Coverage dates, when available, are outer bounds: an interior date can still lack a rate. If discovery reports unavailable coverage metadata, leave coverage unknown.
Take canvas_id and table_name from a staged fx_get_timeseries response. Each registration creates a unique table name; never construct it from the currency pair. Use fx_dataframe_describe to discover the exact names and column types before SQL.
Gates
- Establish the direction before comparing: a rate measures quote units per base unit. Keep that direction consistent across periods and SQL results.
- Before calling an average a full-period result, inspect the returned observation bounds and coverage notice. Missing currency legs on served publication days reduce coverage; weekends and holidays are not missing observations. Report the observed interval and any coverage shortfall instead of filling gaps.
- Treat truncated as a delivery flag, not proof of complete currency coverage. Read coverage notices even when truncated is false.
- Keep the initial requested-range summary for the period question. A continuation summarizes its own remaining interval; do not average page means.
- Check rate_count and summary before interpreting an empty rates map. A summary-only response can contain observations without showing rows; a genuinely empty interval has no summary.
- Use only dataframe tools advertised by the connected deployment. Before dropping a table, obtain the exact name with fx_dataframe_describe and confirm the requested deletion; do not automatically remove caller-owned tables.
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.
- 2d ago First seen · 57 lines · 57 tokens per session scan A 79660be8891c
exchange-rates-guide is a skill published in the GitHub repository cyanheads/exchange-rates-mcp-server (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 57 tokens to every session and 985 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 2026-11-04.
exchange-rates-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| exchange-rates-guidecyanheads/exchange-rates-mcp-server | Skill | 1 | 3d ago | Apache-2.0 | A | 57 | Claude Code |
| usaspending-guidecyanheads/usaspending-mcp-server | Skill | 5 | 3d ago | Apache-2.0 | A | 44 | Claude Code |
| frankfurter-apiNanookAI/frankfurter-api | Skill | 2 | 4mo ago | MIT | A | 46 | Claude Code |
| financetravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 48 | Claude Code, Codex |
| investment-memo-generatortravisjneuman/.claude | Skill | 107 | yesterday | MIT | A | 37 | Claude Code, Codex |
| levyseaworld008/Commonly-used-high-value-skills | Skill | 74 | yesterday | MIT | A | 50 | Claude Code, Codex |
| earnings-call-analyzerseaworld008/Commonly-used-high-value-skills | Skill | 74 | yesterday | MIT | A | 33 | Claude Code, Codex |