onepassword-secrets

onepassword-secrets is a skill for Claude Code from Goodsmileduck/claude-registry. It costs 94 tokens per session (2,382 once invoked), scanned A, original, MIT.

A set of rules for safely using 1Password secrets through the op command-line tool.

In plain words
What is it for?
It is for referencing, injecting, and running with API keys, passwords, tokens, credentials, and environment-file secrets.
Why use it?
It prevents secret values from being printed or embedded in code and requires approval for each 1Password command.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the secrets-skills plugin — 1 skill, 1 hook shipped together

Good fit It is for referencing, injecting, and running with API keys, passwords, tokens, credentials, and environment-file secrets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goodsmileduck/claude-registry/onepassword-secrets
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 Goodsmileduck/claude-registry --skill onepassword-secrets
Clone the repo
git clone --depth 1 https://github.com/Goodsmileduck/claude-registry

Made for: Claude Code.

Or install secrets-skills, the plugin that ships this one along with the rest of its 1 skill, 1 hook.

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 onepassword-secrets

README.md
[![agentmods](https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/onepassword-secrets/github.svg)](https://agentmods.dev/skills/goodsmileduck/claude-registry/onepassword-secrets)
Your own site
<a href="https://agentmods.dev/skills/goodsmileduck/claude-registry/onepassword-secrets"><img src="https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/onepassword-secrets/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 onepassword-secrets

Your own site · 80×15
<a href="https://agentmods.dev/skills/goodsmileduck/claude-registry/onepassword-secrets"><img src="https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/onepassword-secrets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.02382
Opus 5 $0.00047 $0.01191
Sonnet 5 $0.00019 $0.00476
Haiku 4.5 $0.00009 $0.00238

Measured 9d ago against content hash 0831c100cd16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

onepassword-secrets scanned grade A with 2 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 2 executable files (scripts/op_audit.py, scripts/test_op_audit.py), 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 /dev/shm/config.yml

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

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

- **`op run -- <shell|curl|wget|python|node|…>`** is proposed → warn that the child process receives all resolved secrets and can exfiltrate them in the single approved call; ask the user to confirm the child command is
plugins/secrets-skills/skills/onepassword-secrets/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-cutting rules

These rules apply to every operation in this skill without exception.

  • Never print or restate a resolved secret value. If a resolved value appears in output, treat it as compromised and rotate it immediately.
  • Reference secrets only as op://Vault/Item/field (or op://Vault/Item/Section/field). Never embed raw values in code, templates, or responses.
  • Prefer op run over op inject over op read. Each step down the hierarchy increases the risk that a resolved value reaches context or disk.
  • op item get --reveal and op item get with --format json are as dangerous as op read: they print resolved values and must be treated with the same caution.
  • Always scope with --vault to prevent accidental resolution against the wrong vault.
  • The wrapped child in op run -- <cmd> is the real risk surface: the child inherits all resolved environment variables. Network tools, shells, and interpreters can exfiltrate those values in a single approved call.
  • Every op invocation requires explicit approval. Never assume a prior approval covers a new call. Never run op speculatively. Never advise the user to select "always allow" for op.

Setup & auth

The op CLI must be installed, signed in (op signin), and connected to a 1Password account before any secret resolution is possible. Service account authentication uses the OP_SERVICE_ACCOUNT_TOKEN environment variable instead of an interactive session. Biometric unlock requires the desktop app. For installation steps, sign-in flows, and service account configuration, see references/setup-and-auth.md.

Inject secrets

Environment injection (preferred)

Create a .env.tpl file containing only op:// references — no raw values. The template file is safe to commit.

# .env.tpl  (safe to commit — contains references, not values)
DB_URL=op://Production/Postgres/connection-string
OPENAI_API_KEY=op://Production/OpenAI/credential
STRIPE_SECRET=op://Production/Stripe/secret_key

Read the full file on GitHub · 139 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 · 139 lines · 94 tokens per session scan A 0831c100cd16

Subscribe to this mod's changes

onepassword-secrets is a skill published in the GitHub repository Goodsmileduck/claude-registry (1 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 2,382 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.