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/uetzel/autoadhd/vault-extractornpx skills add uetzel/AutoADHD --skill vault-extractorgit 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-extractor)<a href="https://agentmods.dev/skills/uetzel/autoadhd/vault-extractor"><img src="https://agentmods.dev/badge/skills/uetzel/autoadhd/vault-extractor.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 | $0.00102 | $0.02382 |
| Opus 5 | $0.00051 | $0.01191 |
| Sonnet 5 | $0.00020 | $0.00476 |
| Haiku 4.5 | $0.00010 | $0.00238 |
Grade A, and why
vault-extractor 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 4d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault Extractor
You're processing an Inbox note and extracting ALL knowledge into structured Canon entries. This is the most important job in the vault — it's where raw human moments become connected, searchable knowledge.
Read the vault-writer skill too if you need note format details. This skill focuses on the extraction process.
Before You Start
- Read
CLAUDE.mdat vault root (if not already loaded) - Read the vault-writer skill for note formats (frontmatter, emoji headings, provenance)
- Have the target Inbox note open and read every sentence of the
# Rawsection
The Extraction Checklist
For every Inbox note, extract ALL of these:
1. People
Anyone mentioned by name. Before creating a new person:
- Search
Canon/People/for the name - Check ALL
aliasesarrays in existing people entries - If found → update the existing entry (add new info, add to changelog)
- If new → create in
Canon/People/following People Schema (Meta/README/People Schema.md)
2. Events
Anything that happened — meetings, conversations, trips, milestones. Include dates, participants, locations.
- Check
Canon/Events/for same date + location or same subject - If match → enrich existing entry
- If new → create in
Canon/Events/
3. Actions (Tasks)
Scan for task-like language:
- "I need to...", "we should...", "I want to...", "let's..."
- "don't forget...", "reminder:...", "todo:..."
- "I have to...", "we must...", "plan to..."
- German: "ich muss...", "wir sollten...", "ich will..."
For each action:
- Check
Canon/Actions/for existing match - If exists → add new mention to
mentionsarray - If new → create in
Canon/Actions/
Action field rules (enforce every time):
mentions: MUST be array of actual filenames (e.g.2026-03-16 - Voice - mercado.md). NEVER write"multiple memos"or placeholders.first_mentioned: actual earliest date from the memos being processedowner: default"[[Usman Kotwal]]"unless someone else is explicitly stateddue: approximate dates over blank ("by summer" →2026-09-01, "end of April" →2026-04-30)output: one-sentence "done looks like" inferred from context
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.
- 4d ago First seen · 248 lines · 102 tokens per session scan A 3658b752ae50
vault-extractor is a skill published in the GitHub repository uetzel/AutoADHD (22 stars, last pushed 4mo ago), licensed MIT. It adds 102 tokens to every session and 2,382 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…