Claudesidian is a preconfigured Obsidian vault structure that lets Claude Code help manage a personal knowledge base as a thinking partner. It is for people who organize notes and other knowledge in Obsidian, with Git-based version control and optional integrations for image analysis and web research. The catalogue add-ons provide Claude Code skills, agents, hooks, and settings for working with this vault.
Borrowing it
Nothing to install: this file belongs to heyitsnoah/claudesidian. 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/heyitsnoah/claudesidian/main/.agents/skills/upgrade/SKILL.mdgit clone --depth 1 https://github.com/heyitsnoah/claudesidianWrote 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/heyitsnoah/claudesidian/upgrade)<a href="https://agentmods.dev/skills/heyitsnoah/claudesidian/upgrade"><img src="https://agentmods.dev/badge/skills/heyitsnoah/claudesidian/upgrade.svg" alt="Measured on agentmods" 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 | $0.00044 | $0.03108 |
| Opus 5 | $0.00022 | $0.01554 |
| Sonnet 5 | $0.00009 | $0.00622 |
| Haiku 4.5 | $0.00004 | $0.00311 |
Grade D, and why
upgrade scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
diff -q .claude/settings.json .tmp/claudesidian-upgrade/.claude/settings.json 2>/dev/null Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `rm -rf .tmp/claudesidian-upgrade` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
LATEST=$(curl -s https://raw.githubusercontent.com/heyitsnoah/claudesidian/main/package.json | grep '"version"' | head -1 | cut -d'"' -f4) How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Upgrade
Pulls the latest claudesidian from GitHub and merges it into the user's vault, preserving customizations.
Layout assumptions (READ FIRST)
claudesidian stores skills under .agents/skills/<name>/SKILL.md as the
canonical location. Symlinks live at .claude/skills/<name> and
.pi/skills/<name> pointing back to canonical. Edit canonical, all consumers
follow.
If the user is on a pre-conversion claudesidian (anything before the
commands→skills migration) they will have .claude/commands/*.md instead and
no .agents/skills/. Do not run a normal upgrade in that case — see
"Migration from legacy layout" at the bottom of this file.
If the user's local repo has .agents/skills/ populated, proceed normally.
Process
1. Version check
- Read current version from
package.json - Fetch upstream version:
CURRENT=$(grep '"version"' package.json | head -1 | cut -d'"' -f4) LATEST=$(curl -s https://raw.githubusercontent.com/heyitsnoah/claudesidian/main/package.json | grep '"version"' | head -1 | cut -d'"' -f4) if [ "$CURRENT" = "$LATEST" ]; then echo "✅ Already on $CURRENT" exit 0 fi - Detect layout:
test -d .agents/skills && echo NEW || echo LEGACY. If LEGACY, jump to "Migration from legacy layout".
2. Backup
BACKUP_DIR=".backup/upgrade-$(date +%Y-%m-%d-%H%M%S)"
mkdir -p "$BACKUP_DIR"
cp -r .agents .claude .pi .scripts package.json "$BACKUP_DIR/" 2>/dev/null
cp CHANGELOG.md README.md "$BACKUP_DIR/" 2>/dev/null || true
echo "✅ Backup created at $BACKUP_DIR"
3. Fetch upstream
git clone --depth=1 --branch=main \
https://github.com/heyitsnoah/claudesidian.git \
.tmp/claudesidian-upgrade
The user's working repo stays disconnected from origin throughout — we only
ever read from .tmp/.
4. Build upgrade checklist
System files we care about:
- Skills:
.agents/skills/<name>/SKILL.md(canonical) — also resources inside skill dirs (helper scripts, references). - Hooks:
.claude/hooks/*.sh - Settings:
.claude/settings.json - MCP servers:
.claude/mcp-servers/* - Scripts:
.scripts/* - Core:
package.json,CHANGELOG.md,README.md
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 · 329 lines · 44 tokens per session scan D 0b0a1eba3252
upgrade is a skill published in the GitHub repository heyitsnoah/claudesidian (2,583 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 3,108 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (reads agent configuration directories, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
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…
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…