Borrowing it
Nothing to install: this file belongs to ctxpipe-ai/ctxpipe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ctxpipe-ai/ctxpipe/main/.agents/skills/preview-env/auth/SKILL.mdgit clone --depth 1 https://github.com/ctxpipe-ai/ctxpipeWrote 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.
[](https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/auth)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/auth"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/auth/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.
<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/auth"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/auth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00027 | $0.01558 |
| Opus 5.5 | $0.00011 | $0.00623 |
| Sonnet 5.5 | $0.00005 | $0.00312 |
| Haiku 4.5 | $0.00003 | $0.00156 |
Grade A, and why
preview-env-auth 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preview-env auth
Account and membership surface. Runs after onboarding, so account A and the org exist. Harness is PASS. Flow format: run-setup. Accounts B and C use their own browser contexts.
AUTH-1 Session persists
Requires ONB-2 (A has an org). Steps
- As A, reload the current app URL.
Expect (UI) still under /{orgSlug}; SideNav shows this org; sign-in is not shown.
Expect (backend) the same sessions row is still valid (no new session row).
Budget 3 s / 10 s, reload to SideNav visible.
Evidence AUTH-1-1.png; trace of the get-session request.
AUTH-2 Sign out and sign in
Requires AUTH-1; Workspace 1 exists (ONB-4) for the landing check. Steps
- Open sign-out (
/.auth/sign-outor the account control). - Sign in at
/.auth/sign-inwith A's email and password.
Expect (UI) signed out shows the sign-in form; after sign-in the browser lands on /{orgSlug}/ws/{workspace1Slug} (last-used Workspace, new composer). With zero Workspaces it lands on /{orgSlug}/workspaces/new.
Expect (backend) the old sessions row is gone; a new one exists for A.
Budget 3 s / 10 s, submit to composer visible.
Evidence AUTH-2-1.png (sign-in), AUTH-2-2.png (composer); trace of the sign-in request.
AUTH-3 Account chrome and device page
Requires AUTH-1. Steps
- Open
{BASE_URL}/.auth/account; the Settings index (heading user account) renders. - Open
{BASE_URL}/.auth/device; do not submit a code.
Expect (UI) account chrome, not an auth error; on the device page the heading Authorize ctxpipe CLI and a Device code field (placeholder ABCD-1234).
Expect (backend) none (read only).
Budget 3 s / 10 s per page.
Evidence AUTH-3-1.png, AUTH-3-2.png.
AUTH-4 Two-factor (TOTP) enroll and challenge
Requires account B signed in (AUTH-5 done) so A's session stays free of a 2FA challenge; a TOTP generator the run can drive (read the secret from the enrollment screen). Steps
- As B, open account Security (
/.auth/account/security, uncertain path) and enable two-factor with the password. - Add the secret to the generator, submit the 6-digit code, save the backup codes.
- Sign out, sign in as B, and submit a fresh code at the challenge.
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.
- 4d ago First seen · 94 lines · 27 tokens per session scan A e270e41f9b0d
preview-env-auth is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,558 once invoked, about $0.0001 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 2026-10-21.
Other skills, from other repositories
browser-journey-test
Validate user stories by simulating real user journeys in a live browser against deployed application. Activate after implementation to verify actual user experience against acceptance criteria, not just code logic.
sidekick-audit
Deterministic UI quality audit of a web page or a whole product — WCAG 2.2 A/AA accessibility (axe-core), Core Web Vitals (LCP/CLS), browser health (console errors, failed requests, mixed content) and tap-target size — reported dimensions-first, with confirmed-vs-uncertain findings clustered into root-cause families…
sidekick-test
Goal-based end-to-end UI testing that PROVES the outcome. Given a URL and a plain-language goal (e.g. 'sign up, create a project, and invite a teammate'), sidekick drives a real browser to do it and then verifies success with a DETERMINISTIC signal on the real page — the execution agent is never allowed to grade its…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.