vault-unseal

vault-unseal is a skill for Claude Code, Codex from runxhq/runx. It costs 33 tokens per session (673 once invoked), scanned A, original, Apache-2.0.

A controlled workflow for making an approved, short-lived reference to a secret available to one authorized workload without revealing the secret itself.

In plain words
What is it for?
It helps request, approve, create, and verify an opaque secret handle through a compatible vault connection.
Why use it?
It avoids putting secret values into an agent's context and limits access by purpose, scope, principal, and time.

Skill for Claude CodeCodex

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

Good fit It helps request, approve, create, and verify an opaque secret handle through a compatible vault connection.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/runxhq/runx/vault-unseal
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 runxhq/runx --skill vault-unseal
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

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 vault-unseal

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/runxhq/runx/vault-unseal"><img src="https://agentmods.dev/badge/skills/runxhq/runx/vault-unseal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 673 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 35
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00033 $0.00673
Opus 5 $0.00016 $0.00336
Sonnet 5 $0.00007 $0.00135
Haiku 4.5 $0.00003 $0.00067

Measured 9d ago against content hash 8165f75a6002, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

vault-unseal 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.

The scan reads SKILL.md. This mod also ships 1 executable file (vault-unseal.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/vault-unseal/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vault Unseal

Execute one least-privilege request to make an opaque secret reference available to one principal for one purpose, scope, and short access window. The default execute runner sends that exact request through a configured vault adapter after approval and independently reads the resulting handle metadata. vault-unseal remains the explicit plan-only runner. Neither runner retrieves or reveals secret material.

Use it when a later workload needs a bounded secret handle and the request must pass a human approval and real vault adapter. Do not use it as a secret store, credential loader, environment-file parser, or way to put secret values into an agent context.

How it works

  1. Bind the opaque secret reference to the requesting principal, declared purpose, allowed scope, and requested time window.
  2. Validate that the reference is opaque and the TTL is between one minute and one hour.
  3. Reject raw secret-shaped input, ambiguous principals, broad purpose, or unbounded scope.
  4. Emit an approval-ready request and exact provider handoff.
  5. With execute, request approval for that exact plan, invoke secret.unseal under one idempotency key, then call handle.read for the returned opaque reference. Completion requires both provider operations.

The local plan needs no approval because it exposes no secret and changes no provider state. The unseal operation is consequential and remains a separate gate. Credential custody stays in the operator-selected local, self-hosted, third-party, or Runx-hosted vault binding; the package receives no token and owns no request client.

Result and stop conditions

A ready plan contains the bounded request, expiry, approval requirement, and provider handoff with provider_status: not_called and no secret value. A successful execution additionally carries native mutation and handle-readback packets. The provider result is required to expose only an opaque handle_ref, expiry, and status metadata; a raw secret is a provider contract violation. Missing or unsafe inputs return a useful stop packet rather than a guessed request.

Read the full file on GitHub · 68 lines

Files

What ships with it

7 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.

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. 9d ago First seen · 68 lines · 33 tokens per session scan A 8165f75a6002

Subscribe to this mod's changes

vault-unseal is a skill published in the GitHub repository runxhq/runx (87 stars, last pushed 3d ago), licensed Apache-2.0. It adds 33 tokens to every session and 673 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 2026-09-03.