safe-login
Skill2 starsChanged 7 months agoApache-2.0View on GitHub
Authenticate through a standard email and password login form while protecting credentials. Use when a browser task requires a logged-in session and the site does not provide an API.
In this repository8 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/00-project.mdcCursor rule
- .cursor/rules/10-python.mdcCursor rule
- .cursor/rules/20-mcp-tools.mdcCursor rule
- capture-evidence-bundleSkill
- guidelinesSkill
- scrape-with-paginationSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Use this skill for ordinary email/password forms.
- Very specific: line 29
Use get_page_snapshot to identify email/username, password, remember-me, and submit controls.
- Distinctive: line 34
If a TOTP field appears, ask the user for the current code unless one was already provided.
- Very specific: line 37
Use take_screenshot after login only if evidence is needed and it will not expose private account data.
- Distinctive: line 48
Never log or return passwords, TOTP codes, cookies, or auth headers.
- Distinctive: line 49
Never persist credentials in artifacts.
- Distinctive: line 50
Never attempt to bypass CAPTCHA, SSO, passkeys, or account recovery controls.
≈ “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.
Files
Safe Login
When To Use
Use this skill for ordinary email/password forms. Do not use it for SSO, OAuth, passkeys, CAPTCHA solving, or flows that require bypassing security controls.
Inputs
login_urlemailpasswordsuccess_selectoror visible text that confirms login succeeded.totp_codeif the user provides a one-time code during the session.
Procedure
navigate(login_url)and wait for the login form.- Use
get_page_snapshotto identify email/username, password, remember-me, and submit controls. - Type credentials with
type_text. Do not repeat credential values in any response or log. - Submit with
clickorpress_key("Enter"). - If a TOTP field appears, ask the user for the current code unless one was already provided.
wait_forthe success selector or success text.- Use
take_screenshotafter login only if evidence is needed and it will not expose private account data.
Failure Modes
- CAPTCHA or bot challenge: stop and report
captcha. - Password field not found: capture a page snapshot and report
no-form. - Invalid credentials: report the site error text without echoing secrets.
Never
- Never log or return passwords, TOTP codes, cookies, or auth headers.
- Never persist credentials in artifacts.
- Never attempt to bypass CAPTCHA, SSO, passkeys, or account recovery controls.
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
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.

