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 JansenAnalytics/claudex --skill secret-vaultgit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/jansenanalytics/claudex/secret-vault)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/secret-vault"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/secret-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/jansenanalytics/claudex/secret-vault"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/secret-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 | $0.00021 | $0.00599 |
| Opus 5.5 | $0.00008 | $0.00240 |
| Sonnet 5.5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade B, and why
secret-vault scanned grade B 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 2mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
The master key (`~/.openclaw/vault.key`) is 32 random bytes stored with `chmod 600`. Without it the vault is unreadable. How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
secret-vault
Encrypted credential store — AES-256-GCM secured tokens and secrets in one place.
What it does
Keeps API tokens, passwords, and other sensitive values in an encrypted file at ~/.openclaw/vault.enc. Each secret has its own IV and auth tag so no two ciphertexts are alike, even for identical values.
The master key (~/.openclaw/vault.key) is 32 random bytes stored with chmod 600. Without it the vault is unreadable.
Trigger phrases
- "store the token in the vault"
- "get X from the vault"
- "what secrets are in the vault?"
- "add X to the vault"
- "vault set / vault get / vault list"
- "encrypt and store"
- "use getSecret to fetch"
- "vault check" / "verify the vault"
Primary file
${SECRET_VAULT_HOME:-$HOME/projects/secret-vault}/vault.cjs
Symlink (or same file) also lives at:
${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/secret-vault/scripts/vault.cjs
CLI quick reference
node vault.cjs set NAME "value" # store / overwrite
node vault.cjs get NAME # print decrypted value
node vault.cjs list # names only, no values
node vault.cjs delete NAME # remove secret
node vault.cjs export # print encrypted JSON to stdout
node vault.cjs check # verify integrity + count
Programmatic usage
const { getSecret } = require("${SECRET_VAULT_HOME:-$HOME/projects/secret-vault}/vault.cjs");
const token = getSecret("GITHUB_TOKEN"); // returns string or null
Key locations
| File | Purpose | Permissions |
|---|---|---|
~/.openclaw/vault.key |
32-byte master key | 600 |
~/.openclaw/vault.enc |
Encrypted secrets JSON | 600 |
Security model
- AES-256-GCM — authenticated encryption (detects tampering)
- Unique random IV per secret (16 bytes)
- Auth tag per secret (16 bytes)
- Values never logged or printed in
list - Export blob is safe to back up; useless without the key
What ships with it
4 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.
- 2mo ago First seen · 79 lines · 21 tokens per session scan B 134dde899107
secret-vault is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 599 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
secret-vault compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| secret-vaultJansenAnalytics/claudex | Skill | 5 | 4mo ago | MIT | B | 21 | Claude Code, Codex |
| frontmcp-deploymentagentfront/frontmcp | Skill | 148 | yesterday | Apache-2.0 | A | 244 | Claude Code, Codex |
| doris-debug-nodeapache/doris-skills | Skill | 49 | 3d ago | Apache-2.0 | A | 50 | Claude Code, Codex |
| harness-init-runnerrexleimo/aios | Skill | 62 | yesterday | MIT | A | 68 | Claude Code, Codex |
| enigmagent-vaultAgnuxo1/EnigmAgent | Skill | 7 | 6d ago | MIT | A | 42 | Claude Code, Codex |
| clawhubAgnuxo1/EnigmAgent | Skill | 7 | 6d ago | MIT | A | 0 | Claude Code, Codex |
| vnshraullenchai/vnsh | Skill | 158 | 2mo ago | MIT | D | 51 | Claude Code, Codex |