Borrowing it
Nothing to install: this file belongs to uetzel/AutoADHD. 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/uetzel/AutoADHD/main/.claude/skills/vault-writer/SKILL.mdgit clone --depth 1 https://github.com/uetzel/AutoADHDWrote 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/uetzel/autoadhd/vault-writer)<a href="https://agentmods.dev/skills/uetzel/autoadhd/vault-writer"><img src="https://agentmods.dev/badge/skills/uetzel/autoadhd/vault-writer/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/uetzel/autoadhd/vault-writer"><img src="https://agentmods.dev/badge/skills/uetzel/autoadhd/vault-writer.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 | $0.00130 | $0.02811 |
| Opus 5.5 | $0.00052 | $0.01124 |
| Sonnet 5.5 | $0.00026 | $0.00562 |
| Haiku 4.5 | $0.00013 | $0.00281 |
Grade A, and why
vault-writer 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 2mo 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault Writer
You're writing notes in an Obsidian vault that serves as a personal operating system. Every note follows specific rules so that AI agents (Extractor, Reviewer, Implementer) can process them reliably, and so the human can scan them visually with ADHD-friendly formatting.
This skill contains everything you need. Don't rely on remembering CLAUDE.md — the rules are right here.
The Golden Rules
- Provenance is sacred. Every fact traces to a human moment or explicit source. Add
source:to frontmatter. Add<!-- source: ... -->comments on AI-added content. - Locked fields are untouchable. If frontmatter has a
locked:array, those fields cannot be changed by AI. Period. If new info contradicts a locked field, keep the locked value. - Wikilinks are structure. Every mention of a known person, event, concept, action, decision = a wikilink. Before linking, verify the target exists. If it doesn't, create a stub or note it's missing.
- Never touch
# Rawsections. Raw transcripts in Inbox notes are source evidence. Read-only. - Never fabricate. If unsure, say so.
Frontmatter Template
Every note needs at minimum:
---
type: person | event | concept | decision | project | action | place | organization | reflection | belief | emerging | ai-reflection
name: Human Readable Name
created: YYYY-MM-DD
updated: YYYY-MM-DD
source: voice | human | ai-extracted | ai-generated | ai-enriched
---
Additional fields are welcome when useful (aliases, status, tags, linked, locked, etc.) but not required except for specific types below.
Source Values
voice— spoken by human in a voice memohuman— typed/written directly by humanai-extracted— AI pulled from a voice memo transcriptai-generated— AI created (research, enrichment, reflection)ai-enriched— AI added content to a human-created note
Agent Attribution (MANDATORY)
Every AI action must identify WHICH agent did it and WHEN. Generic "ai-generated" is not enough.
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.
- 2mo ago First seen · 307 lines · 130 tokens per session scan A bd81474b7c35
vault-writer is a skill published in the GitHub repository uetzel/AutoADHD (25 stars, last pushed 6mo ago), licensed MIT. It adds 130 tokens to every session and 2,811 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
vault-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vault-writeruetzel/AutoADHD | Skill | 25 | 6mo ago | MIT | A | 130 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |