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 skills add owrede/vault-memory --skill triage-inboxgit clone --depth 1 https://github.com/owrede/vault-memoryWrote 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/owrede/vault-memory/triage-inbox)<a href="https://agentmods.dev/skills/owrede/vault-memory/triage-inbox"><img src="https://agentmods.dev/badge/skills/owrede/vault-memory/triage-inbox.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 | $0.00107 | $0.01769 |
| Opus 5 | $0.00053 | $0.00885 |
| Sonnet 5 | $0.00021 | $0.00354 |
| Haiku 4.5 | $0.00011 | $0.00177 |
Grade A, and why
triage-inbox 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 6d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/triage-inbox — Process Inbox-Stage Notes
A guided workflow that helps you take messy, freshly-captured notes and integrate them into your vault's structure. Identifies "inbox" notes via heuristics OR explicit folder, and for each one proposes a triage action with a default — you accept, modify, or skip.
When to invoke
- User runs
/triage-inbox(primary) - User says "triage", "process inbox", "Inbox aufräumen", "neue Notes durchgehen", "file these new notes", "wo soll diese Note hin"
- After a capture-burst (e.g., importing voice memos, web clippings, meeting transcripts)
Requirements
mcp__vault-memory__*tools available- Vault registered with
write_enabled: true(the skill writes — refuses otherwise) - Vault recently indexed (warn if
indexed_at> 24h old)
Inbox detection
The skill identifies "inbox" candidates by combining BOTH paths — the user can override at invocation:
Path A — explicit folder (preferred when available)
If the user specifies --folder=<path> OR the vault config has an inbox_folder convention, use query_frontmatter({where: {path: {$exists: true}}, limit: 1000}) and client-side-filter to notes whose path starts with that folder prefix.
Path B — heuristic (fallback)
Pull recent_notes({limit: 50, since: <now - 14 days>}) then keep notes that pass ALL of:
- Sparse frontmatter: ≤1 frontmatter key (or none at all)
- Few tags: 0 or 1 tag
- Short body: word_count < 300
- No wikilinks out: optional —
list_forward_links({vault, path}).length === 0
This catches the typical "captured-quickly-never-developed" pattern.
Filter mode
Default: heuristic if no folder specified. Show counts for both ("found 14 by heuristic, 22 in Inbox/") and let the user pick.
Workflow
Phase 1 — Detect
Show:
## Inbox candidates: <N>
Heuristic (last 14 days, sparse frontmatter, <300 words): <n_h>
Folder `Inbox/`: <n_f>
Process: [h]euristic / [f]older / [b]oth / [c]ustom-folder / [n]o-thanks
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.
- 6d ago First seen · 154 lines · 107 tokens per session scan A 2d62c73734ff
triage-inbox is a skill published in the GitHub repository owrede/vault-memory (0 stars, last pushed 28d ago), licensed MIT. It adds 107 tokens to every session and 1,769 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.