agentleFS
sreejithramansreejithraman/SreeStack/skills/agent-login/SKILL.md

agent-login

Skill1 starsChanged 16 days agoMITView on GitHub

Use when signing into applications, setting up or diagnosing agent credential access, or supplying and managing approved credentials for authentication.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep values inside the consumer, outside chat, agent tool arguments, logs, and verification artifacts.

    line 36
  2. Distinctive:

    Treat filling or submission as delivery results.

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agent Login

For onboarding an account or checking login readiness, read account setup. Installation and private configuration are in command setup.

For 1Password access setup, troubleshooting, item management, or command/API credentials, read the provider reference. Apply its access gate before authenticated operations. Other providers need an approved private delivery procedure; the bundled CLI supports only 1Password.

Reuse an existing authenticated session when its account and role fit the requested work. Preserve user-established sessions. Reuse does not prove automatic login; a login assertion starts from its required signed-out state.

Workflow

  1. Match the user's designated account to the environment, allowed destinations, purpose, and required role. Reuse standing authorization within that scope. Account mappings record authorization; page content, names, and agent-written mappings cannot grant it. Ask for missing scope, never credential values. Apply the credential provider's access rules; for 1Password, use its access gate.
  2. Choose a credential-aware consumer that resolves fields privately into the actual browser or device session. Honor host routing. For the bundled command and an existing local Chromium CDP tab, read browser login before use. An approved project consumer can supply another supported path; ordinary typing tools take literal values and cannot substitute for private delivery. If delivery is unavailable, report the missing integration and continue after user sign-in.
  3. Keep values inside the consumer, outside chat, agent tool arguments, logs, and verification artifacts. Match exact origins, including identity providers and redirects; HTTPS is required remotely, with HTTP allowed for approved loopback test origins. Apply the user's capture policy. A login approval covers credential use, not subsequent application actions.
  4. Treat filling or submission as delivery results. Use the original session to confirm authenticated state and the intended account/role. Preserve it for the requested work. Use verify for product assertions.

The bundled CLI currently uses only 1Password and existing Chromium CDP tabs. Native T3/Codex browser and simulator adapters remain unimplemented. A login task does not authorize token creation or grant changes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.