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 egroup-labs/kept --skill vaultgit clone --depth 1 https://github.com/egroup-labs/keptWrote 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/egroup-labs/kept/vault)<a href="https://agentmods.dev/skills/egroup-labs/kept/vault"><img src="https://agentmods.dev/badge/skills/egroup-labs/kept/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/egroup-labs/kept/vault"><img src="https://agentmods.dev/badge/skills/egroup-labs/kept/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 | $0.00045 | $0.00362 |
| Opus 5.5 | $0.00018 | $0.00145 |
| Sonnet 5.5 | $0.00009 | $0.00072 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
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 1mo 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.
What it actually says
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 structurelist_directory— Browse a specific folderread_file— Read a conversation or notewrite_file— Create a new file (fails if exists)update_file— Overwrite an existing file (fails if missing)delete_file— Remove a filemove_file— Move or rename a filegrep_vault— Regex search across all markdown files
Workflow Rules
- Search before creating. Always
grep_vaultorlist_vaultto check if content already exists before writing new files. - Confirm destructive operations. Before
delete_fileormove_file, tell the user what you're about to do and get confirmation. - Cite sources. When referencing content from vault files, cite by conversation title and file path.
- Respect structure. Vault uses
provider/conversation-title.mdlayout (e.g.,claude/my-chat.md,chatgpt/session.md). Follow this when creating files. - Use grep for content questions. "Did we discuss X?" →
grep_vault. "What's in this file?" →read_file. "What files exist?" →list_vault.
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.
- 1mo ago First seen · 28 lines · 45 tokens per session scan A fe750b2ccb5c
vault is a skill published in the GitHub repository egroup-labs/kept (147 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 362 once invoked, about $0.0002 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.
Other skills, from other repositories
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
pages
Browse, open, or print distilled pages, reusing the wenlan pages CLI for the actual open (one implementation on your PATH, no setup). /wenlan pages opens the page when one matches, or shows a small native picker when 2-4 match. /wenlan pages --print reads the page here instead of opening an editor. /wenlan pages lists…
slm-media
Save pictures and PDFs in SuperLocalMemory and find them again by describing them. Covers when to save a picture or document, remembermedia, rememberdocument, getmedia, mediastatus and mediauploadlink, how recall returns pictures and PDF pages, the limits, what stays private, turning the feature on with slm media (16…
searxng-kg-ingestion
Persist SearXNG search results into the epistemic-graph knowledge graph via the searxng-mcp MCP server. Use when the agent must turn a web search into durable, semantically-searchable KG memory — each result becomes a :Document (plus :SearchQuery and :SearchEngine typed nodes with :resultOf / :fromEngine links) so…
omni-context-memory
Use the user's Omni-Context long-term memory when it is connected over MCP. Trigger this whenever you need to recall what the user has done, decided, or prefers across past conversations. Do not write anything unless the user explicitly asks to save or remember it. Omni-Context is a local knowledge graph — NOT the…
mnemazina
An agent workflow that turns files and links placed in a Desktop inbox into checked, categorized notes for Obsidian, a note-taking application. It also updates section contents, a master index, and an action-oriented summary.