enigmagent-vault

enigmagent-vault is a skill for Claude Code, Codex from Agnuxo1/EnigmAgent. It costs 42 tokens per session (1,905 once invoked), scanned A, original, MIT.

A secure vault workflow for using credentials, API keys, and private documents through placeholders instead of exposing their contents to the AI agent. The real values are inserted only when a command runs.

In plain words
What is it for?
Use it when running commands that need named secrets, domain logins, or stored documents, with references such as {{GITHUB_TOKEN}} or {{DOC:report.md}}.
Why use it?
It keeps secrets out of the agent’s reasoning, tool arguments, and generated output while still allowing commands to use them.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when running commands that need named secrets, domain logins, or stored documents, with references such as {{GITHUB_TOKEN}} or {{DOC:report.md}}.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/agnuxo1/enigmagent/enigmagent-vault
Install

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.

Any agent
npx skills add Agnuxo1/EnigmAgent --skill enigmagent-vault
Clone the repo
git clone --depth 1 https://github.com/Agnuxo1/EnigmAgent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for enigmagent-vault

README.md
[![agentmods](https://agentmods.dev/badge/skills/agnuxo1/enigmagent/enigmagent-vault/github.svg)](https://agentmods.dev/skills/agnuxo1/enigmagent/enigmagent-vault)
Your own site
<a href="https://agentmods.dev/skills/agnuxo1/enigmagent/enigmagent-vault"><img src="https://agentmods.dev/badge/skills/agnuxo1/enigmagent/enigmagent-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.

agentmods 80×15 button for enigmagent-vault

Your own site · 80×15
<a href="https://agentmods.dev/skills/agnuxo1/enigmagent/enigmagent-vault"><img src="https://agentmods.dev/badge/skills/agnuxo1/enigmagent/enigmagent-vault.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,905 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01905
Opus 5 $0.00021 $0.00953
Sonnet 5 $0.00008 $0.00381
Haiku 4.5 $0.00004 $0.00191

Measured 10d ago against content hash 956cf982a633, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

enigmagent-vault scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

You write: curl -H "Authorization: Bearer {{GITHUB_TOKEN}}" https://api.github.com
platforms/hermes-agent/skills/security/enigmagent-vault/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EnigmAgent Vault — Secure Credential Usage

Core principle

Never ask the user for credentials. Never write credentials in tool arguments. Use {{PLACEHOLDER}} references instead — they are resolved to real values after you generate the tool call, before the tool executes.

The LLM (you) writes the placeholder. The gateway injects the real value. You never see it. The user's secrets stay private.

You write:   curl -H "Authorization: Bearer {{GITHUB_TOKEN}}" https://api.github.com
Gateway:     resolves {{GITHUB_TOKEN}} → injects ghp_xxxxxxxxxxxx → runs curl
You receive: the HTTP response body (200 OK, user data, etc.)

Placeholder syntax

Pattern Example Use case
{{NAME}} {{GITHUB_TOKEN}} Any named secret
{{LOGIN:domain}} {{LOGIN:gmail.com}} Login password for a domain
{{DOC:filename}} {{DOC:report.md}} Full text of a stored document

Names are case-insensitive. Use the exact name shown by enigmagent_vault_list.


Step 1 — Check vault is ready

Before any task involving credentials, call:

Tool: enigmagent_vault_status

If running: false: Tell the user:

"The EnigmAgent vault server is not running. Please open a new terminal and run: enigmagent-mcp --mode rest --port 3737 --vault ~/.enigmagent/vault.json Then try again."

Do NOT proceed until the vault is running.

If running: true, unlocked: false: Tell the user:

"The vault server is running but locked. Please restart it: enigmagent-mcp --mode rest --port 3737 --vault ~/.enigmagent/vault.json"

If running: true, unlocked: true: Proceed. All {{PLACEHOLDER}} references will work.


Step 2 — Discover available secrets

When you need a credential and are unsure of the exact name, call:

Tool: enigmagent_vault_list

This lists all secrets by name and domain. Use the exact name field as your placeholder. Never guess names — always check the list first.

Example output:

{
  "count": 4,
  "entries": [
    {"name": "GITHUB_TOKEN",      "domain": "localhost"},
    {"name": "OPENAI_API_KEY",    "domain": "localhost"},
    {"name": "LOGIN:gmail.com",   "domain": "localhost"},
    {"name": "DOC_contract.md",   "domain": "localhost"}
  ]
}

Read the full file on GitHub · 242 lines

Changes

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.

  1. 10d ago First seen · 242 lines · 42 tokens per session scan A 956cf982a633

Subscribe to this mod's changes

enigmagent-vault is a skill published in the GitHub repository Agnuxo1/EnigmAgent (4 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 1,905 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.