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 xonika9/agent-skills --skill x9-personal-vaultgit clone --depth 1 https://github.com/xonika9/agent-skillsWrote 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/xonika9/agent-skills/x9-personal-vault)<a href="https://agentmods.dev/skills/xonika9/agent-skills/x9-personal-vault"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-personal-vault/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/xonika9/agent-skills/x9-personal-vault"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/x9-personal-vault.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 | $0.00144 | $0.00777 |
| Opus 5.5 | $0.00058 | $0.00311 |
| Sonnet 5.5 | $0.00029 | $0.00155 |
| Haiku 4.5 | $0.00014 | $0.00078 |
Grade A, and why
x9-personal-vault 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personal vault
The file script supports macOS and Linux.
It turns a folder, plus any other folders the user names, into a personal vault built on the vault model, and leaves the daily rules inside the vault. Ordinary agent sessions then keep the vault in order without this skill; the skill is needed again only when the structure changes.
Select the action
- Set up: the vault has no
x9-personal-vaultblock in itsAGENTS.md, including a folder that already has its own structure. Follow setup. - Change structure: add an
areavalue or a stream, rename, merge, or remove a topic or stream, or change the vault's rules. Follow changes. - Check: report where the vault drifted from its rules. Follow changes.
Infer the action from the request and the folder's state.
Ownership
- This skill owns the vault model, the vault's templates and how-to note, and the block between
<!-- x9-personal-vault:start -->and<!-- x9-personal-vault:end -->in the vault'sAGENTS.mdand, when the agent starts in a parent folder, in that folder'sAGENTS.md, written per agents-block. Text outside the markers belongs to the user. x9-obsidianowns link-preserving moves inside an Obsidian vault and Bases files; use it for those when Obsidian is in use.x9-okf-docsowns the OKF header of every note outside the vault's exclusions and its own block in the vault'sAGENTS.md.- A file that the vault's
AGENTS.mdassigns to another skill, or that belongs to another app, is placed or linked, never rewritten.
Boundaries
- Inspection, the conversation, and the plan change nothing. Changes start only after the user approves the plan or names the exact change.
- Read only the target folder, its parent's
AGENTS.mdandCLAUDE.mdwhen the agent starts there, and the paths the user names. - Deleting a user's file needs its own confirmation naming that file or folder, after the user has seen its verified copy. Merging an inbox note into its place is a move, not a deletion.
- Offer Git as local-only. A remote, sync service, or sharing setup is the user's separate decision; a vault with health or financial records stays private.
- Human-facing files are written in the user's language; the
AGENTS.mdblock is written in English.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 41 lines · 144 tokens per session scan A 5912a54803ec
x9-personal-vault is a skill published in the GitHub repository xonika9/agent-skills (4 stars, last pushed 4d ago), licensed MIT. It adds 144 tokens to every session and 777 once invoked, about $0.0006 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 2026-10-13.
Other skills, from other repositories
gog-workspace
Use the gog CLI for Google Workspace tasks across Gmail, Calendar, Drive, Docs, Sheets, Contacts, and related services. Use when the user asks to check email, search Gmail, inspect calendar events, find Drive files, read Docs or Sheets, or manage Google Workspace data through gog.
notion
Read and write Notion pages, databases (data sources), and blocks via the Notion REST API.
obsidian-workout-export
Export workout data to an Obsidian-formatted Markdown file. Always trigger immediately when the user types "owd". Also trigger on "export workout", "obsidian workout", "save workout to obsidian", or related requests to export workout data into Obsidian. Read the current conversation first before searching prior…
file_engine
Create, convert (including DOCX to PDF), patch, and replace Knowledge files through one file-engine workflow.
mcp_lark
Operate the user's connected Lark account or legacy Lark/Feishu app. Use for reading chats and messages, sending or replying to text messages, reading and writing document content, and listing, creating or updating Bitable records.
lark-cli
Lark/Feishu (飞书) CLI tool. Use when the user asks to do anything on Lark/Feishu.