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/met-museum-mcp-server --skill techniquesgit clone --depth 1 https://github.com/cyanheads/met-museum-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/met-museum-mcp-server/techniques)<a href="https://agentmods.dev/skills/cyanheads/met-museum-mcp-server/techniques"><img src="https://agentmods.dev/badge/skills/cyanheads/met-museum-mcp-server/techniques/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/met-museum-mcp-server/techniques"><img src="https://agentmods.dev/badge/skills/cyanheads/met-museum-mcp-server/techniques.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 | $0.00079 | $0.00487 |
| Opus 5 | $0.00039 | $0.00244 |
| Sonnet 5 | $0.00016 | $0.00097 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade A, and why
techniques 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 10d 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.
This is a copy
100% identical to techniques — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Overview
A directory of cross-cutting techniques for shaping what a handler returns and how a client retrieves it — patterns that don't belong to a single API surface. Each entry is a self-contained reference under references/: the problem it solves, when to reach for it (and when not to), and how to apply it with current framework primitives.
These are patterns, not new primitives — they compose tool(), output/format() shaping, ctx.state, and the existing helpers. Where a technique has (or will have) a dedicated helper, its reference says so and links the tracking issue.
Techniques
| Technique | Path | Use when |
|---|---|---|
| Outline-on-overflow | references/outline-on-overflow.md |
A single tool call returns one document-shaped payload too big to inline (e.g. a ~130KB record), and you want an honest section outline + a re-call contract instead of truncating. |
Adding a technique
One file under references/, one row above. A technique earns a place here when it's a reusable response/retrieval pattern that (a) spans more than one tool or server and (b) isn't already covered by an api-* reference. Keep the reference concise: problem → when-to-use → how-to with current primitives → helper status. Bump metadata.version on any change (skill-versioning policy).
Related
design-mcp-server— choosing the tool surface and output shapes up front.add-tool— thetool()builder,format()⟷structuredContentparity, matching response density to context budget.api-canvas—spillover(), the row-collection sibling of outline-on-overflow.
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.
- 10d ago First seen · 33 lines · 79 tokens per session scan A 8f01d620e53c
techniques is a skill published in the GitHub repository cyanheads/met-museum-mcp-server (4 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 487 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to techniques, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
bun-runtime-http
Covers Bun.serve, HTTP server configuration, routing, streaming responses, WebSockets, TLS/SSL, and middleware with Bun's native APIs.
bun-guides-process
Guides for child processes, IPC, spawning commands, and signal handling with Bun.$ and Bun.spawn.
bun-guides-streams
Guides for working with WHATWG Streams, ReadableStream, WritableStream, and TransformStream in Bun.
bun-guides-write-file
Guides for writing files, appending data, atomic writes, and streaming file output in Bun.
bun-guides-websocket
Guides for building real-time WebSocket servers, pub/sub, client connections, and auto-reconnect in Bun.
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.