a2aproject/a2a-samples is a collection of code examples showing how AI agents communicate and delegate tasks through the Agent2Agent protocol, a shared way for agents built with different frameworks or languages to interoperate. Developers use it to learn and build multi-agent systems, with examples that include an agent server and a client host. The catalogue skill is one of the repository's agent-oriented additions.
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/a2aproject/a2a-samples/frankfurternpx skills add a2aproject/a2a-samples --skill frankfurtergit clone --depth 1 https://github.com/a2aproject/a2a-samplesWrote 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/a2aproject/a2a-samples/frankfurter)<a href="https://agentmods.dev/skills/a2aproject/a2a-samples/frankfurter"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-samples/frankfurter.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 5.1 | $0.00014 | $0.00418 |
| Opus 5 | $0.00007 | $0.00209 |
| Sonnet 5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
frankfurter 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 6d 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.
What it actually says
frankfurter
Fetch currency exchange rates from the frankfurter.dev API.
get_latest_rates
Retrieve the latest exchange rates.
- Base URL: https://api.frankfurter.dev
- Method: GET
- Endpoint: /v1/latest
- Parameters:
- base (string): The base currency symbol (default: EUR).
- symbols (string): A comma-separated list of target currency symbols to filter.
get_historical_rates
Retrieve exchange rates for a specific past date.
- Base URL: https://api.frankfurter.dev
- Method: GET
- Endpoint: /v1/{date}
- Parameters:
- date (string, required): The date in YYYY-MM-DD format.
- base (string): The base currency symbol.
- symbols (string): A comma-separated list of target currency symbols.
get_time_series_rates
Retrieve exchange rates over a specific time period.
- Base URL: https://api.frankfurter.dev
- Method: GET
- Endpoint: /v1/{start_date}..{end_date}
- Parameters:
- start_date (string, required): Start date (YYYY-MM-DD).
- end_date (string): End date (YYYY-MM-DD). If omitted, defaults to the current date.
- base (string): The base currency symbol.
- symbols (string): A comma-separated list of target currency symbols.
get_available_currencies
Retrieve a list of all available currency symbols and their full names.
- Base URL: https://api.frankfurter.dev
- Method: GET
- Endpoint: /v1/currencies
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.
- 6d ago First seen · 52 lines · 14 tokens per session scan A d4880d024fec
frankfurter is a skill published in the GitHub repository a2aproject/a2a-samples (1,757 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14 tokens to every session and 418 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
mistake-reflection
Use when you discover you made a mistake — caught by the user, by a tool result, by your own re-reading, or by a failed check. Appends a structured entry to docs/ai/ailearnings.md and re-reads recent entries to avoid repeats.
a2a-adapter
Use when building A2A Protocol agents, converting AI agents from any framework (LangChain, CrewAI, n8n, LangGraph, Ollama, or custom) into A2A-compatible servers, or working with the a2a-adapter Python SDK.
grocery-prices
A skill to calculate grocery prices with country-specific taxes.
fix-tck-issue
Analyzes and fixes A2A Transport Compatibility Kit (TCK) issues by understanding the specification, reproducing the failure, implementing the fix, and validating it works.
release-a2a
Guide maintainers through the multi-step release process — version bump, CI verification, tagging, Maven Central deployment, SNAPSHOT bump, and versioned documentation.
update-a2a-proto
Update the A2A Protobuf file (a2a.proto) when the A2A protocol specification changes. Use when the user mentions updating the spec, syncing with upstream A2A, or when a new version of the A2A protocol is released.