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 instructions/nanookai/frankfurter-api/agents-mdgit clone --depth 1 https://github.com/NanookAI/frankfurter-apiWrote 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/instructions/nanookai/frankfurter-api/agents-md)<a href="https://agentmods.dev/instructions/nanookai/frankfurter-api/agents-md"><img src="https://agentmods.dev/badge/instructions/nanookai/frankfurter-api/agents-md.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 | $0.00556 | $0.00556 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
frankfurter-api AGENTS.md scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
against the live API (`curl https://api.frankfurter.dev/v2/...`) before it goes How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This repository contains an Agent Skill that teaches AI agents how to use the Frankfurter exchange rate API (https://frankfurter.dev/). The deliverable is documentation, not application code.
Layout
skills/frankfurter-api/SKILL.md— skill entry point (frontmatter + quick reference)skills/frankfurter-api/references/endpoints.md— full v2 endpoint referenceskills/frankfurter-api/references/v1-api.md— legacy v1 API notes
Conventions
- English only in all files. No Chinese or other non-English text in any committed file, including examples and comments.
- Verify before documenting. Every request/response example must be checked
against the live API (
curl https://api.frankfurter.dev/v2/...) before it goes into the docs. Do not copy response shapes from memory — the API evolves. - v2 is the primary API. New content goes in
SKILL.md/endpoints.md.v1-api.mdexists only for people maintaining legacy code; keep it minimal. - Keep SKILL.md lean (well under 500 lines). Detailed material belongs in
references/, with a clear pointer from SKILL.md telling the reader when to open it. - Explain the why. When documenting a pitfall or rule, state the reason (e.g. "Cloudflare returns 403 for the default Python-urllib User-Agent") so agents can generalize instead of pattern-matching.
Known live-API facts worth preserving
These were discovered by testing and are not in the official docs:
- The public API returns 403 for the default
Python-urllibUser-Agent (Cloudflare).curl,fetch, andpython-requestswork; a customUser-Agentfixesurllib. - Weekends/holidays have no new data; the returned
datefield is authoritative. - Error bodies look like
{"status": 404, "message": "not found"}.
Validation checklist before committing
grep -rnP '[\x{4e00}-\x{9fff}]' . --exclude-dir=.gitreturns nothing (no CJK text).- Any changed example URL was re-run against the live API.
- SKILL.md frontmatter still has valid
nameanddescriptionfields, and the description stays short (~1-2 sentences) while keeping trigger keywords: exchange rate, currency conversion, forex, historical FX.
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.
- 5d ago First seen · 46 lines · 556 tokens per session scan A 392d5451e473
frankfurter-api AGENTS.md is an instructions file published in the GitHub repository NanookAI/frankfurter-api (2 stars, last pushed 2mo ago), licensed MIT. It adds 556 tokens to every session, about $0.0028 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
pg-aiguide CLAUDE.md
Claude Code instructions for timescale/pg-aiguide, covering tiger docs mcp server - development guidelines, build, test & run commands, code style guidelines and python (ingest/).
supergraph AGENTS.md
AGENTS.md instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
markifact-mcp GEMINI.md
Instructions for markifact/markifact-mcp, covering markifact, the 8 tools, discover → inspect → run, connection vs account and reporting workflow.
bundles-forge AGENTS.md
Instructions for OdradekAI/bundles-forge, covering project knowledge base, structure, where to look, conventions and anti-patterns (this project).
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
technical-product-gtm AGENTS.md
Instructions for beingsmit/technical-product-gtm, covering agents.md, what this is, how to use these skills, what makes these skills different and author.