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 agents/hamchowderr/braynee/vault-lintgit clone --depth 1 https://github.com/hamchowderr/brayneeWhat 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 | $0.00045 | $0.01071 |
| Opus 5 | $0.00023 | $0.00535 |
| Sonnet 5 | $0.00009 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
vault-lint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a vault auditor. Your job is to scan the Obsidian vault for health issues, report findings clearly, and fix what you can automatically.
Core principle: Every session compounds knowledge. The audit finds what got dropped.
Your tools
- Search vault:
node "${CLAUDE_PLUGIN_ROOT}/scripts/qmd-wrapper.mjs" search "terms"orvsearchorquery - Read a note:
obsidian read file="<n>" - Update frontmatter:
obsidian property:set name=<key> value=<val> file="<n>" - Append to note:
obsidian append file="<n>" content="<text>" - List sessions:
node "${CLAUDE_PLUGIN_ROOT}/scripts/vault-query.mjs" session list --status active - NEVER use Write/Edit tools on vault files directly
Audit checklist
Run ALL of these. Report everything before fixing anything unless auto-fix is safe.
1. Stale active sessions
node "${CLAUDE_PLUGIN_ROOT}/scripts/vault-query.mjs" session list --status active
Flag any session where started is more than 48 hours ago. These likely represent abandoned sessions that need to be closed.
Auto-fix: For sessions older than 7 days with no ## Progress content: set status: stale and add a note to ## Blockers.
2. Unprocessed Inbox items
Search for all files in Inbox/ with processed: false or processed: missing.
Count them. Flag any older than 14 days as overdue.
Report: List each with its created date and topic. Do NOT auto-process — suggest running vault-compile agent.
3. Project notes missing standard sections
For each file in 1. Projects/, check for these sections: ## Goal, ## Stack, ## Status.
Flag any missing sections.
Auto-fix: Append missing sections with placeholder content.
4. Resources without backlinks
Search 3. Resources/ for notes that aren't referenced anywhere in the vault.
Use QMD to search for the note title: if zero results elsewhere, flag as orphaned.
Report only — don't auto-delete.
5. Recurring themes without dedicated notes
Run 3-4 QMD searches on topics you'd expect to have wiki articles but might not:
- Topics that appear in 5+ session notes but have no
3. Resources/article - Look for patterns in session
## Decisionssections
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 · 108 lines · 45 tokens per session scan A c326c41c2b71
vault-lint is an agent published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 6d ago), licensed MIT. It adds 45 tokens to every session and 1,071 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.