Borrowing it
Nothing to install: this file belongs to ljcl/strava-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ljcl/strava-mcp/main/.agents/skills/mcp-authoring/SKILL.mdgit clone --depth 1 https://github.com/ljcl/strava-mcpWrote 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/ljcl/strava-mcp/mcp-authoring)<a href="https://agentmods.dev/skills/ljcl/strava-mcp/mcp-authoring"><img src="https://agentmods.dev/badge/skills/ljcl/strava-mcp/mcp-authoring/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/ljcl/strava-mcp/mcp-authoring"><img src="https://agentmods.dev/badge/skills/ljcl/strava-mcp/mcp-authoring.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 | $0.00082 | $0.01346 |
| Opus 5 | $0.00041 | $0.00673 |
| Sonnet 5 | $0.00016 | $0.00269 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade A, and why
mcp-authoring 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 9d 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 mcp-authoring — 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring MCP Servers and Apps
Guidance for building high-quality MCP servers and apps. This file is the spine:
read it first, then open the reference that matches your task. Examples use the
official MCP TypeScript SDK (@modelcontextprotocol/sdk); the principles apply to
any SDK. Examples target @modelcontextprotocol/sdk v1.x; v2 wraps tool input/output schemas in z.object().
The four primitives: when to use each
| You need | Use a | Examples |
|---|---|---|
| To do something (effects, mutations, API calls) | Tool | send-email, create-issue, search-orders |
| To expose read-only data the client can fetch | Resource | app config, a user profile, a doc by URI |
| A reusable, user-invoked interaction template | Prompt | review-code, summarize-thread |
| A visual surface (browse, compare, select) | App / UI | a results grid, a calendar, a dashboard |
Quick rules of thumb:
- Tool vs Resource: a tool acts and is model-invoked; a resource is data and is client-fetched. If it has side effects, it is a tool.
- Prompt: user-initiated, not model-initiated. Surfaced as a slash command or menu item in the host. Don't use prompts for things the model should call itself.
- UI: add one when seeing beats reading (browsing many items, comparing side-by-side, or interactive selection). See references/mcp-apps-ui.md.
Core principles
- Tools for actions, resources for data, prompts for templates, UI for sight. Pick the primitive that matches the intent, not the one that's easiest to wire up.
- One tool = one capability. Split broad actions into focused tools.
create-user/delete-user/list-users, notmanage-users. - Return complete data upfront. Tool calls are expensive round-trips. Don't make
the model call
listthenget-detailsN times; return the details with the list. - Describe everything. Every tool, every schema field, every resource gets a description written for a cold model that has never seen your service. The description is the API.
- UI owns UI-state; the server owns domain data. Selections, filters, and tabs live in the UI locally, not as extra tools and not on the server.
- Validate at boundaries only. Validate and sanitize user input and external API responses. Trust your own internal code; don't add error handling for things that can't happen.
- Prefer UI for browsing and comparing. When in doubt and the data is visual, a UI surface improves the experience.
What ships with it
5 files 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.
- 9d ago First seen · 108 lines · 82 tokens per session scan A 42fc7211cd66
mcp-authoring is a skill published in the GitHub repository ljcl/strava-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,346 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 mcp-authoring, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…