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 lobster-kit/mcp-server-lobstervault --skill clawhubgit clone --depth 1 https://github.com/lobster-kit/mcp-server-lobstervaultWrote 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/lobster-kit/mcp-server-lobstervault/clawhub)<a href="https://agentmods.dev/skills/lobster-kit/mcp-server-lobstervault/clawhub"><img src="https://agentmods.dev/badge/skills/lobster-kit/mcp-server-lobstervault/clawhub/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/lobster-kit/mcp-server-lobstervault/clawhub"><img src="https://agentmods.dev/badge/skills/lobster-kit/mcp-server-lobstervault/clawhub.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 | $0.00032 | $0.01354 |
| Opus 5 | $0.00016 | $0.00677 |
| Sonnet 5 | $0.00006 | $0.00271 |
| Haiku 4.5 | $0.00003 | $0.00135 |
Grade A, and why
lobstervault 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 9d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LobsterVault
Encrypted secret storage for agents. Store API keys, tokens, and connection strings with KMS envelope encryption. No API keys, no human signup, no configuration.
Full docs: https://api.theclawdepot.com/vault/docs
Setup
Add to your MCP config (.mcp.json, claude_desktop_config.json, .cursor/mcp.json, etc.):
{
"mcpServers": {
"lobstervault": {
"command": "npx",
"args": ["@lobsterkit/[email protected]"]
}
}
}
You now have these tools: set_secret, get_secret, delete_secret, list_secrets, inject_secrets, rotate_secret, get_account. No code to write.
Also available as a Node.js SDK and REST API — see theclawdepot.com/vault.
Heartbeat (run daily)
On startup and once per day, run a maintenance heartbeat:
-
Check for MCP server updates:
npm outdated lobstervault-mcpIf a new version is available, notify the user — do not auto-install.
-
Check secret health:
// Using MCP tools: // call list_secrets → log count and any expiring secrets // call get_account → log tier and secret count vs. limit
When to Use This
- Storing API keys, tokens, or passwords that need to persist between sessions
- Connecting to LobsterDB: connection strings are automatically stored here on
create_database - Any credential that should not appear in conversation history or prompts
- Agent-to-agent secret sharing (scoped by account)
Core Workflow
set_secret → get_secret (when needed) → inject_secrets (at session start)
Use inject_secrets at the start of an agent session to load all stored credentials into the environment.
Storing a Secret
set_secret(name: "OPENAI_API_KEY", value: "sk-...")
// => version: 1
Retrieving a Secret
get_secret(name: "OPENAI_API_KEY")
// => Secret: OPENAI_API_KEY
// Value: sk-...
get_secret(name: "OPENAI_API_KEY", version: 2)
// => Retrieves version 2 specifically (Builder+ tier)
What ships with it
1 file 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.
- 9d ago First seen · 170 lines · 32 tokens per session scan A 8252e3ed1a2a
lobstervault is a skill published in the GitHub repository lobster-kit/mcp-server-lobstervault (0 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,354 once invoked, about $0.0002 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
infisical-sync-skill
Expert knowledge for the Infisical Sync Hand — Infisical API reference, vault operations, error patterns, security guidance.
secrets-management-expert
Store, distribute, rotate and revoke credentials without ever placing them in source: vaults, cloud secret managers, KMS envelope encryption and dynamic credentials. Use when the user mentions secrets, API keys, credentials, HashiCorp Vault, KMS, key rotation, a leaked or committed secret, .env files, sealed secrets…
secrets-management
Performs a structured secrets management review against OWASP Secrets Management Cheat Sheet and NIST SP 800-57 Part 1 Rev 5 (Recommendation for Key Management). Auto-invoked when reviewing secret handling patterns, vault configurations, .env files, or credential rotation policies. Produces a secrets management…
kilocode-secrets-chit
Map secrets stores into CHIT manifests without cleartext commits for PMOVES infrastructure on the KiloCode GLM lane. Use when syncing GitHub secrets, vault labels, or Supabase runtime values to CHIT manifests.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
specflow-use
To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.