cloudgeni-ai/opengeni/secrets

Claude Code and agent skill by cloudgeni-ai/opengeni

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when signing in, creating accounts, storing or using passwords, API keys, TOTP codes or other secrets, or when a secret is missing.

Install

npx vskill@latest install cloudgeni-ai/opengeni/secrets

SKILL.md

Secrets: sign in and use credentials yourself

Use references instead of viewing values. Sign in, create accounts when the task allows it, enroll 2FA, fetch codes and solve CAPTCHAs yourself.

References

WriteResolves to
{{secret:Item}}the primary field (password of a login, value of an API key)
{{secret:Item/field}}one field, such as {{secret:GitHub/username}}
{{secret:Vault/Item/field}}a field in a named vault
{{secret:Item/otp}}the current TOTP code, computed when the action runs
{{secret:Item/field#previous}}the version before the current one
{{secretfile:Item}}a temporary file path holding the value (shell commands)
\{{secret:Item}}the literal text, left unresolved

A reference resolves where something runs: shell commands, typing, files, run_on and connector calls. Opengeni tools that store or send text (messages, goals, notes, Slack posts) keep it as text for later work. Escape it (\{{secret:Item}}) where something runs first, such as ogtool call. secret_* tools take references as names.

Tools

  • secret_search: metadata and references, never values. No filters lists all;

page one lists vaults. Follow nextCursor with unchanged filters. Check complete and freshness before inferring absence. refresh: true requests fresh inventory without bypassing rate limits.

  • secret_save: each field takes value, generate, fromReference or

restoreVersion. Generate new passwords.

  • secret_move: move or copy to another vault.
  • secret_delete: archive an item.
  • secret_get: plaintext with secrets:read, only if references cannot work.

Login ladder

Go down the list and stop at the first rung that gets you in. None of these needs the user's permission.

  1. Reuse a saved browser session (browser identity or browser_auth).
  2. Sign in with a saved login: {{secret:Item/username}}, {{secret:Item}},

then {{secret:Item/otp}} at the code prompt. When the item shows hasPasskey, the managed browser already holds its passkey: choose the site's passkey sign-in instead.

  1. After signing in, enroll your own TOTP so the next login needs no one.
  2. Get email or SMS codes and magic links through connected mail or

messaging tools.

  1. No account and the task allows creating one: create it, saving a generated

password with secret_save before you submit the form.

  1. Only the user has it: ask with a secret card.
  2. Hand the browser to the user only for a push approval or a hardware key.

CAPTCHAs are always yours. Solve them with screenshots, the audio option, a reload or another attempt. Never hand a CAPTCHA to the user, and do not stop after one failure.

Saving

  • saveTo: user (Only me, reused later), task (throwaway, shared with this

task's sessions) or workspace (team keys, schedules that run without you).

  • Name items by service/account; record websites and username.
  • Respect provider capabilities. Ask cards save to hosted vaults only.

Provider write and move limits: references/troubleshooting.md.

Missing secrets and errors

A tool result with secret_reference_error ran nothing. For a missing secret it includes askCard: call request_human_input with it, changing only saveTo or prompt, then retry with the returned reference.

An unavailable or incomplete provider is not a missing secret: respect retry times or reconnect/unlock it. Inspect unknown write outcomes before retrying; never repeat a create just because its inventory refresh failed.

Playbooks

  • Login: references/login-playbook.md.
  • Sign-up: references/account-creation.md.
  • TOTP: references/2fa-enrollment.md.
  • CLI/files: references/api-keys.md.
  • Secret card: references/ask-card.md.
  • Errors: references/troubleshooting.md.
  • Escaping: references/codemode-and-scripts.md.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
205
Repository forks
18
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/cloudgeni-ai/opengeni/secrets/badge)](https://verified-skill.com/skills/cloudgeni-ai/opengeni/secrets)

Something wrong with this skill or its page? Tell us.