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/national-parks-mcp-server --skill add-skillgit clone --depth 1 https://github.com/cyanheads/national-parks-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/national-parks-mcp-server/add-skill)<a href="https://agentmods.dev/skills/cyanheads/national-parks-mcp-server/add-skill"><img src="https://agentmods.dev/badge/skills/cyanheads/national-parks-mcp-server/add-skill/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/national-parks-mcp-server/add-skill"><img src="https://agentmods.dev/badge/skills/cyanheads/national-parks-mcp-server/add-skill.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 | $0.00095 | $0.02523 |
| Opus 5.5 | $0.00038 | $0.01009 |
| Sonnet 5.5 | $0.00019 | $0.00505 |
| Haiku 4.5 | $0.00010 | $0.00252 |
Grade A, and why
add-skill 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 yesterday.
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 add-skill — 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
A server has two skill trees, written for different readers:
| Tree | Reader | Written by |
|---|---|---|
framework-skills/ |
The agent building the server | init and the maintenance sync, plus any development skills of the server's own |
skills/ (root) |
The agent that installed the server and is calling its tools | The author, deliberately |
Root skills/ is absent by default; init and maintenance never write it. Claude Code always scans a plugin's root skills/ (Agent Plugins 1.0.0 fixes discovery there), so no skills field is needed in .claude-plugin/plugin.json. Each SKILL.md follows the Agent Skills specification; a host skips one that doesn't, without a word, which is why lint:packaging validates the tree.
No skill by default
Publish one only when an agent calling the tools needs something instructions and tool descriptions cannot carry: a multi-hop identifier chain, a gate that prevents a wrong call or a wrong conclusion, a query syntax. Overview skills that restate the tool list, generic "how to use this server" workflows, and skills for hypothetical tasks do not ship.
Authoring rules
- Perspective. The reader is the agent calling the server's tools in the middle of a multi-step task, not the maintainer. Walk a realistic workflow against the tool surface and write down what that agent needs at each hop.
- One skill per server, split by trigger. The description stays resident in every session; the body loads only on invocation, so workflows belong inside the one skill, not in a second with the same trigger. A second skill earns its place only when a distinct trigger vocabulary routes to a materially different workflow. Two is the cap; three when day-to-day use of the server proves it.
- Naming. Default
<package short name>-guide(pubmed-guideforpubmed-mcp-server). The description names the tool prefix (pubmed_*) so the agent binds the skill to the tools it sees. - Layering. Tool
.describe()text carries the per-tool contract;instructionscarries a one-paragraph orientation (canonical chain, identifier types, rate posture); MCP prompts stay user-invoked task templates. The skill carries what none of those can: when to reach for the server and when not to, where each opaque identifier comes from, gates, branching workflows, and syntax references. It never restatesinstructions. - Gates are the section a skill exists for. Each is an imperative the agent satisfies before acting or concluding: a precondition (resolve a name to an ID before filtering, where an unresolved filter returns the global set), a stop rule (confirm coverage before reporting a record absent), or a confirmation gate (ask the user before a tool that sends, writes, or deletes). Verified facts only, sourced from
instructions, the design doc's Workflow Analysis and Known Limitations, tool descriptions, or closed issues — nothing invented. Cut any fact that would not change what the agent does. - Drift. Name tools in prose; never list their parameters — the schemas own them.
- Budget.
SKILL.mdunder 150 lines (the specification's 500 is a ceiling, not a target); the description under 500 characters, since it is resident in every session. Long material goes toreferences/.
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.
- yesterday First seen · 139 lines · 95 tokens per session scan A 0d4497574def
add-skill is a skill published in the GitHub repository cyanheads/national-parks-mcp-server (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 95 tokens to every session and 2,523 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to add-skill, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
internet-archive-guide
Use ia tools to investigate historical web pages or Internet Archive books and documents. Resolve capture and item identities, compare the captures actually served, and check coverage before claiming content absent or fully read.
oecd-guide
Build SDMX keys, confirm which series an OECD dataflow actually carries, and read oecd results without mixing units, breakdowns, or country aggregates. Use when calling oecd tools for cross-country statistics (GDP, growth, unemployment, labour, education, tax), when a query returns noresults or invalidkey, or when a…
usgs-water-guide
Gates and workflows for the water tools over USGS stream gages and groundwater wells. Covers whether a river or aquifer is high or low right now, telling live gages from discontinued ones, reading depth-to-water rankings (they run inverted), finding the parameter code a site actually reports, time zones and data lag…
release-and-publish
Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.clientCapabilities, ctx.enrich, ctx.content), and when to use each.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.