What is automic-vault-credentials?

A guide for using Automic Vault, a macOS credential manager that stores secrets in the Keychain and requires human approval for each use. It covers credentials such as GitHub tokens, API keys, SSH keys, and signing keys.

It helps list available credentials, inject one into a command, check approval history, diagnose blocked operations, and inspect which tools Automic Vault supports.

Agents need access to credentials for commands such as GitHub, AWS, Docker, SSH, or Git signing without seeing secret values. The guide explains how to request access and investigate approvals or failures.

automic-vault-credentials — Skill for Claude Code by technicalpickles

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 technicalpickles/pickled-claude-plugins --skill automic-vault-credentials

Clone the repo

git clone --depth 1 https://github.com/technicalpickles/pickled-claude-plugins

Made for: Claude Code.

Or install automic-vault, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/automic-vault-credentials/github.svg)](https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/automic-vault-credentials)

Your own site

<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/automic-vault-credentials"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/automic-vault-credentials/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/automic-vault-credentials"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/automic-vault-credentials.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 778 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00088	$0.00778
Opus 5.5	$0.00035	$0.00311
Sonnet 5.5	$0.00018	$0.00156
Haiku 4.5	$0.00009	$0.00078

Measured 23d ago against content hash 942a6eaa3e21, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

automic-vault-credentials 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 23d 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.

plugins/automic-vault/skills/automic-vault-credentials/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using Automic Vault (`av`)

Overview

av is the CLI for Automic Vault, a macOS app that holds credentials in the Keychain and makes a human approve each use. It is the credential manager here, not 1Password, not gh auth token, not a .env file. You never see secret values and shouldn't try to. You ask, a person approves in the app or on their phone, and the command runs.

Quick Reference

Need	Do
See what's available	`av list` (names only)
Run a command that needs a secret	`av inject +NAME -- cmd args`
Secret not saved yet	Ask the user to run `av save NAME` (or `av save --project-directory=. NAME`). You can't type it for them
Tool already hardened (`gh`, `aws`, `docker`, `ssh`, git signing)	Run the tool normally. Approval happens behind it
Why was something denied or slow	`av history --json --since 1h --no-pager`
Is hardening intact	`av doctor <tool>`
Does `av` cover tool X, or how do I do Y	`av hardeners --json` lists supported tools. Then `av help` and https://www.automicvault.com/docs/ (start at "Choosing a Mechanism"). Say "not sure yet" before "can't"

Errors

You see	Cause	Do
`approval service is blocked by this process's sandbox`	Your Bash sandbox can't reach the approval service	Rerun that one command outside the sandbox
`gh` says token invalid or sends an empty auth header, but works in the user's terminal	Same sandbox block (older `gh` Isotope hides the message)	Rerun that one `gh` call outside the sandbox
`Approval presentation interrupted` in `av history`	Prompt couldn't be shown: sandbox, or app not running	Rerun outside the sandbox. If it persists, ask the user to run `av open`
`Secrets are unavailable from Keychain ... (-25308)`	Mac is locked	Ask the user to unlock and retry, or enable Available While Locked for that credential. Never skip signing
`agent refused operation` (ssh or signing)	Policy denied, prompt unanswered, or locked	Read `av history` for the request and its decision, then report that

Read the full file on GitHub · 43 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.

23d ago First seen · 43 lines · 88 tokens per session scan A 942a6eaa3e21

Subscribe to this mod's changes

automic-vault-credentials is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (12 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 778 once invoked, about $0.0004 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 2026-10-18.

Claude Code Security buildkite claude-skills monorepo workflow

automic-vault-credentials next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
automic-vault-credentialstechnicalpickles/pickled-claude-plugins	Skill	12	today	MIT	A	88	Claude Code
create-agent-dotnetdiagrid-labs/dapr-skills	Skill	13	4d ago	MIT	A	58	Claude Code
create-pubsub-dotnetdiagrid-labs/dapr-skills	Skill	13	4d ago	MIT	A	79	Claude Code
create-pubsub-pythondiagrid-labs/dapr-skills	Skill	13	4d ago	MIT	A	70	Claude Code
create-workflow-from-diagramdiagrid-labs/dapr-skills	Skill	13	4d ago	MIT	A	97	Claude Code
create-workflow-typescriptdiagrid-labs/dapr-skills	Skill	13	4d ago	MIT	A	69	Claude Code
create-workflow-dotnetdiagrid-labs/dapr-skills	Skill	13	4d ago	MIT	A	52	Claude Code