Borrowing it
Nothing to install: this file belongs to OlliMakarova/mcp-metro. 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/OlliMakarova/mcp-metro/master/.claude/skills/upgrade-sdk/SKILL.mdgit clone --depth 1 https://github.com/OlliMakarova/mcp-metroWrote 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/ollimakarova/mcp-metro/upgrade-sdk)<a href="https://agentmods.dev/skills/ollimakarova/mcp-metro/upgrade-sdk"><img src="https://agentmods.dev/badge/skills/ollimakarova/mcp-metro/upgrade-sdk/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/ollimakarova/mcp-metro/upgrade-sdk"><img src="https://agentmods.dev/badge/skills/ollimakarova/mcp-metro/upgrade-sdk.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 | $0.00103 | $0.08471 |
| Opus 5 | $0.00051 | $0.04235 |
| Sonnet 5 | $0.00021 | $0.01694 |
| Haiku 4.5 | $0.00010 | $0.00847 |
Grade A, and why
upgrade-sdk 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 upgrade-sdk — 17 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 — 632 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FA-MCP-SDK Upgrader
Execute an end-to-end upgrade of the fa-mcp-sdk dependency in the current project: analyze the diff between two
versions, present an actionable execution plan, get user confirmation, apply the changes automatically (asking for any
inputs needed along the way), verify, and report.
Operating principle
Maximize automation. Do as much as possible inside this skill. The only items that should end up on a "manual" checklist are those the LLM genuinely cannot perform from within this session (e.g. they depend on production secrets it has no way to obtain, or on coordination with humans in external systems). When the LLM can perform a step but needs information from the user — a credential, a config value with no sensible default, a choice between alternatives, confirmation about overwriting a locally-customized file — it must ask the user inline rather than punt the task to the manual list.
The user expects: confirm the plan → upgrade is fully done by the time the skill finishes. Failures must be reported with concrete next-step options (retry, fix, roll back, leave-as-is) — never silently swallowed.
Workflow at a glance
1. Parse arguments → resolve FROM/TO refs
2. Validate refs → fail fast on bogus versions
3. Preflight safety → branch + uncommitted-changes check
4. Install TO into project → run `install-target-sdk.mjs` (yarn add + copy update-sdk.js + run it)
5. Analyze diff → categorize every change as Auto / Needs-Input / Manual
6. Build execution plan
7. PRESENT PLAN + CONFIRM ← blocking gate; nothing else mutates until user says go
8. Execute Auto items, ask user inline for Needs-Input items as we reach them
9. Verify (build, lint, typecheck, tests, clean startup)
10. Report (chat + claudedocs/upgrade-sdk-<FROM>-to-<TO>.md)
Step 1: Argument parsing
Parse $ARGUMENTS to extract a target version and an optional language hint.
Language detection
Look anywhere in the arguments for a natural-language phrase indicating the desired output language:
- "in Russian", "ru" → Russian
- "in English", "en" → English
- Any similar phrase or ISO 639-1 code.
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 · 632 lines · 103 tokens per session scan A b027ec843c60
upgrade-sdk is a skill published in the GitHub repository OlliMakarova/mcp-metro (0 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 8,471 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to upgrade-sdk, differing in 17 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…