obsidian-mcp: Skill for Claude Code

.claude/skills/upgrade/SKILL.md

upgrade is a skill for Claude Code from jclement/obsidian-mcp. It costs 68 tokens per session (1,298 once invoked), scanned A, original, MIT.

A skill for updating a project's runtime, packages, container images, and automated build workflows to stable current versions.

In plain words
What is it for?
Use it to update Node.js, Bun, npm dependencies, Docker bases, or GitHub Actions while running type checks, tests, builds, and startup checks.
Why use it?
It limits upgrade risk by avoiding very new or pre-release versions, updating in manageable groups, and checking the project after each group.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is jclement/obsidian-mcp's own configuration. It tells Claude Code how to work on obsidian-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything obsidian-mcp configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is PUBLIC_URL= bun src/server.ts # smoke boot: migrations apply, listens, then Ctrl-C.

Reuse

Borrowing it

Nothing to install: this file belongs to jclement/obsidian-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.

Copy the file
curl -O https://raw.githubusercontent.com/jclement/obsidian-mcp/main/.claude/skills/upgrade/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jclement/obsidian-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for upgrade

README.md
[![agentmods](https://agentmods.dev/badge/skills/jclement/obsidian-mcp/upgrade.svg)](https://agentmods.dev/skills/jclement/obsidian-mcp/upgrade)
Your own site
<a href="https://agentmods.dev/skills/jclement/obsidian-mcp/upgrade"><img src="https://agentmods.dev/badge/skills/jclement/obsidian-mcp/upgrade.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,298 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.01298
Opus 5 $0.00034 $0.00649
Sonnet 5 $0.00014 $0.00260
Haiku 4.5 $0.00007 $0.00130

Measured 8d ago against content hash 56f85791fe6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

upgrade 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 8d 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.

.claude/skills/upgrade/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Upgrade

Keep the stack current without chasing bleeding edge. The goal is "latest soaked stable," not "latest published."

Soaking policy (the guardrails)

  1. Let releases soak. Don't adopt a version that's too fresh — regressions surface in the first couple of weeks.
    • patch/minor: prefer ≥ ~2 weeks old.
    • major: prefer ≥ ~4 weeks old, and read the changelog first.
    • If the only available version of a needed fix is fresh, take it but say so.
  2. Runtimes track the current Active LTS, never "Current"/odd lines. Node: the even LTS in maintenance/active phase (today that's Node 24). Never an odd/Current Node in the image or .mise.toml.
  3. Never adopt pre-release / alpha / beta / next-tag. Check npm view <pkg> dist-tags. If latest ≠ the newest version, the newest is a pre-release — ignore it.
  4. One major per commit. Patch/minor bumps batch together; each major gets its own commit so a bad one is easy to revert and bisect.
  5. Verify after every batch (see Verification). A bump isn't done until tsc + tests + CSS build + a smoke boot all pass.
  6. Respect the hold list. Some deps are deliberately pinned below latest; don't bump them without re-checking the reason.

Where versions are pinned (keep these in sync)

  • npm deps: package.json carets are the allowed range; the committed bun.lock is the exact pin. --frozen-lockfile in both the Dockerfile and CI enforces it. After bumping a floor, run bun install and commit the updated bun.lock.
  • Toolchain: .mise.toml pins Bun and Node to exact versions (not majors). CI's setup-bun bun-version must match the .mise.toml bun pin.
  • Docker base images: pinned to exact patch tags (node:<x.y.z>, node:<x.y.z>-slim, oven/bun:<x.y.z> — both the build FROM and the COPY --from). Optional hardening: pin by @sha256: digest.

When you bump any of these, update all of its locations in the same commit.

Project hold list (re-evaluate, don't blindly bump)

Read the full file on GitHub · 76 lines

Changes

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.

  1. 8d ago First seen · 76 lines · 68 tokens per session scan A 56f85791fe6f

Subscribe to this mod's changes

upgrade is a skill published in the GitHub repository jclement/obsidian-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 1,298 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens