Agent skill

Vault

by egroup-labs in egroup-labs/kept

Search, read, write, and manage files in the Kept conversation vault.

MITAuto-check passedKnowledge Management

Install Vault

skills CLI
$ npx skills add egroup-labs/kept --skill vault -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install egroup-labs/kept vault --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/egroup-labs/kept.git skills-src && mkdir -p .claude/skills && cp -r skills-src/mcp/skills/vault .claude/skills/vault && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vault
GitHub stars
144
Token cost
~372 tokens
SKILL.md length
164 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Search, read, write, and manage files in the Kept conversation vault.

  • Works in 5 steps: Search before creating. Always… → Confirm destructive operations. Before… → Cite sources. When referencing content… → …
  • The user asks about past conversations
  • SKILL.md covers Tools Available and Workflow Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Vault is an agent skill from egroup-labs/kept. Search, read, write, and manage files in the Kept conversation vault. Use when the user asks about past conversations, wants to save notes, needs to find specific content, or wants to organize their vault.

Its SKILL.md is about 370 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management. It works with Model Context Protocol, Obsidian and Chrome Extensions. The repository describes itself as: Search, archive, and recall your AI conversations. ChatGPT, Claude, Gemini, Grok, Kimi. Local-first, MIT licensed. The licence is MIT.

When your agent uses it

  • The user asks about past conversations
  • Wants to save notes
  • Needs to find specific content
  • Wants to organize their vault

Example prompts

  • “/vault”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Search before creating. Always grep_vault or list_vault to check if content already exists before writing new files.
  2. Confirm destructive operations. Before delete_file or move_file, tell the user what you're about to do and get confirmation.
  3. Cite sources. When referencing content from vault files, cite by conversation title and file path.
  4. Respect structure. Vault uses provider/conversation-title.md layout (e.g., claude/my-chat.md, chatgpt/session.md). Follow this when…
  5. Use grep for content questions. "Did we discuss X?" → grep_vault. "What's in this file?" → read_file. "What files exist?" → list_vault.

What it can do on your machine

Read from SKILL.md and the folder at commit c81d59f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vault loads about 372 tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 164 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~372

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from egroup-labs/kept at commit c81d59f, republished under its MIT licence (© egroup-labs). 164 words, ~372 tokens.

Download SKILL.mdSave it as .claude/skills/vault/SKILL.md (or your agent's skills folder).
name
vault
description
Search, read, write, and manage files in the Kept conversation vault. Use when the user asks about past conversations, wants to save notes, needs to find specific content, or wants to organize their vault.

Kept Vault

You have access to the user's Kept vault — a local folder of markdown files capturing AI conversations from ChatGPT, Claude, and Gemini.

Tools Available

  • list_vault — Browse vault structure
  • list_directory — Browse a specific folder
  • read_file — Read a conversation or note
  • write_file — Create a new file (fails if exists)
  • update_file — Overwrite an existing file (fails if missing)
  • delete_file — Remove a file
  • move_file — Move or rename a file
  • grep_vault — Regex search across all markdown files

Workflow Rules

  1. Search before creating. Always grep_vault or list_vault to check if content already exists before writing new files.
  2. Confirm destructive operations. Before delete_file or move_file, tell the user what you're about to do and get confirmation.
  3. Cite sources. When referencing content from vault files, cite by conversation title and file path.
  4. Respect structure. Vault uses provider/conversation-title.md layout (e.g., claude/my-chat.md, chatgpt/session.md). Follow this when creating files.
  5. Use grep for content questions. "Did we discuss X?" → grep_vault. "What's in this file?" → read_file. "What files exist?" → list_vault.

© egroup-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in mcp/skills/vault of egroup-labs/kept.

Open the folder on GitHubat commit c81d59f

Compare with similar skills

Vault next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vault compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vault this skillegroup-labs/kept144—~372Automated safety check: PassMIT
Swarmvaultswarmclawai/swarmvault709—~6.1kAutomated safety check: PassMIT
Engraphdevwhodevs/engraph171—~792Automated safety check: PassMIT
Competitor Feedbackzhitongblog/solomd1.2k—~1.2kAutomated safety check: NotesMIT
Confluence To Markdowniurykrieger/claude-bedrock1051 repos~2.8kAutomated safety check: NotesMIT
Solomdzhitongblog/solomd1.2k—~2kAutomated safety check: PassMIT

Similar skills

  • Swarmvault

    swarmclawai/swarmvault

    Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval…

    709 GitHub stars~6.1k tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed
  • Engraph

    devwhodevs/engraph

    Index and search document collections using hybrid semantic + graph + full-text search.

    171 GitHub stars~792 tokensUpdated 4 mo ago
    Knowledge ManagementAuto-check passed
  • Competitor Feedback

    zhitongblog/solomd

    Scan competing markdown editors' user feedback (GitHub issues/discussions/releases + closed-source forums) and synthesize themes cross-referenced against SoloMD's own gaps and roadmap.

    1.2k GitHub stars~1.2k tokensUpdated today
    Knowledge ManagementAuto-check: notes
  • Confluence To Markdown

    iurykrieger/claude-bedrock

    Internal fetcher module for Confluence pages. An agent skill from iurykrieger/claude-bedrock.

    105 GitHub starsUsed in 1 repo~2.8k tokens
    Knowledge ManagementAuto-check: notes
  • Solomd

    zhitongblog/solomd

    Read, search, edit, and version-control any folder of Markdown notes via the SoloMD MCP server.

    1.2k GitHub stars~2k tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Kb Workflow

    willynikes2/knowledge-base-server

    Use before starting any non-trivial task to search the knowledge base for context, and after completing work to capture findings.

    183 GitHub stars~1.1k tokensUpdated 5 days ago
    Knowledge ManagementAuto-check passed

Questions about Vault

What does Vault do?

Search, read, write, and manage files in the Kept conversation vault. Vault is an agent skill from egroup-labs/kept. Search, read, write, and manage files in the Kept conversation vault.

When should I use Vault?

Vault fits situations like: the user asks about past conversations; wants to save notes; needs to find specific content; wants to organize their vault.

How do I install Vault in Claude Code?

Run `npx skills add egroup-labs/kept --skill vault -a claude-code`. Or copy the skill folder (mcp/skills/vault in egroup-labs/kept) into .claude/skills/vault in your project. Claude Code loads it when a task matches its description.

How do I install Vault in Codex?

Run `npx skills add egroup-labs/kept --skill vault -a codex`. Or copy the skill folder (mcp/skills/vault in egroup-labs/kept) into .agents/skills/vault in your project. Codex loads it when a task matches its description.

Can I use Vault in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add egroup-labs/kept --skill vault -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vault, .gemini/skills/vault, .github/skills/vault and .opencode/skills/vault in your project.

What does Vault need to run?

SKILL.md names no scripts, command-line tools or credentials: Vault is instructions for the agent only.

Does Vault access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Vault safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Vault use?

Vault is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vault use?

About 372 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Vault?

Skills that share tags, products or a category with Vault: Swarmvault (swarmclawai/swarmvault, 709 stars), Engraph (devwhodevs/engraph, 171 stars), Competitor Feedback (zhitongblog/solomd, 1.2k stars) and Confluence To Markdown (iurykrieger/claude-bedrock, 105 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vault?

egroup-labs (a GitHub organization) maintains it in egroup-labs/kept, which has 144 GitHub stars. The repository was last updated on June 15, 2026.

Source: egroup-labs/kept on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.