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 agentmods add skills/howie126313/obsidian-vault-kit/github-syncnpx skills add Howie126313/obsidian-vault-kit --skill github-syncgit clone --depth 1 https://github.com/Howie126313/obsidian-vault-kitWhat 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 | $0.00040 | $0.00737 |
| Opus 5 | $0.00020 | $0.00368 |
| Sonnet 5 | $0.00008 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
github-sync 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Sync — Subagent Dispatcher
When this skill is triggered, do not execute sync steps yourself. Immediately use the Agent tool to launch an independent subagent in the background to handle the entire sync workflow.
Dispatch
Call the Agent tool with the following parameters:
Agent({
description: "GitHub Sync",
model: "sonnet",
run_in_background: true,
mode: "bypassPermissions",
prompt: <full content of the sync-workflow block below>
})
After dispatching, inform the user that sync has started in the background. They can continue other work and will be notified on completion.
sync-workflow
Pass the following content as the Agent prompt (copy verbatim, do not modify):
Step 1: Environment Detection & Status Check
1a. Detect project root and remote (run in parallel):
git rev-parse --show-toplevel # project root
git remote get-url origin # remote URL
git branch --show-current # current branch
1b. Check Git status:
git status
git diff --stat
If there are no changes (no unstaged modifications, no untracked files), output "Nothing to sync" and end.
Step 2: Analyze Changes and Update README.md
2a. Categorize all changed files into three groups:
- Added: new articles or directories
- Modified: updated content
- Deleted: removed content
2b. Update README.md:
- Read current README.md content
- Use
Glob("**/*.md")to scan the project directory structure, count Markdown files (exclude .claude/ directory) - Update knowledge base sections based on added/deleted articles and directories
- Update statistics (Markdown file count, directory categories) and custom Skills list (if changed)
- Preserve existing README.md format and style
Update principle: only update sections with actual changes, do not rewrite unnecessarily.
Step 3: Commit and Push
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.
- 2d ago First seen · 96 lines · 40 tokens per session scan A 39d7a18ca23b
github-sync is a skill published in the GitHub repository Howie126313/obsidian-vault-kit (3 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 737 once invoked, about $0.0002 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.
Other skills, from other repositories
llm-wiki
Build and maintain an LLM-curated personal knowledge base — the "LLM Wiki" pattern from Andrej Karpathy's April 2026 gist. Use this skill whenever the user wants to ingest a source (paper, article, transcript, PDF, notes) into a persistent compounding knowledge base, ask a question against accumulated notes, lint or…
librarian
Orchestrate vault knowledge workflows using the Librarian MCP server. Ingest solutions, search prior art, explore the knowledge graph, log daily learnings.
auto-mode
Set the wiki auto-enrichment mode for the current session — ClaudeAsk (default, propose + always confirm), Hybrid (auto-save type-safe items, ask on high-stakes), FullAuto (auto-save everything with safety nets), or off (no proactive suggestions). Pass "persist" to write OBSIDIANROUTERAUTOENRICH= to the workspace…
llm-wiki-kb
Build and maintain personal knowledge bases as LLM-compiled markdown wikis, inspired by Andrej Karpathy's LLM Wiki pattern. The LLM incrementally ingests raw sources (articles, papers, repos, images) into a structured, interlinked wiki of .md files — with summaries, entity pages, concept pages, cross-references, and a…
validate
Check that an Open Knowledge Format (OKF) bundle is conformant with the v0.2 spec (§11). Use when asked to validate, lint, or check an OKF bundle, or before committing changes to one. Runs a deterministic Python checker — not an eyeball pass. Also migrates a v0.1 bundle to v0.2 in place with --migrate.
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.