Borrowing it
Nothing to install: this file belongs to capad-xyz/searchts. 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/capad-xyz/searchts/main/.opencode/skills/verify-login-lifecycle/SKILL.mdgit clone --depth 1 https://github.com/capad-xyz/searchtsWrote 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/capad-xyz/searchts/verify-login-lifecycle)<a href="https://agentmods.dev/skills/capad-xyz/searchts/verify-login-lifecycle"><img src="https://agentmods.dev/badge/skills/capad-xyz/searchts/verify-login-lifecycle/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/capad-xyz/searchts/verify-login-lifecycle"><img src="https://agentmods.dev/badge/skills/capad-xyz/searchts/verify-login-lifecycle.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 | $0.00091 | $0.00732 |
| Opus 5.5 | $0.00036 | $0.00293 |
| Sonnet 5.5 | $0.00018 | $0.00146 |
| Haiku 4.5 | $0.00009 | $0.00073 |
Grade A, and why
verify-login-lifecycle 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 17d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify the login lifecycle
The artifact this produces is a transcript, not a pass/fail line. It exists because the review question for a safety feature is not "do the tests pass" but "what does a person actually see, in what order, and what is left behind". A green suite cannot answer that; this can.
Run it and paste the output into the PR. It is shorter than the diff and answers the questions the diff raises.
What it proves, and what it cannot
It drives the real searchts CLI and the real MCP surface, with a temporary
USERPROFILE, so:
- Correctness. Each of the four states produces its own distinct, recognisable output, and the two files that must never merge stay distinct.
- Intent. The consent question appears exactly where the design says it should, and nowhere else.
- No residue. Nothing is written to a real store.
It cannot prove a real site accepts a real login. That needs a human at a browser, and the script says so rather than implying otherwise.
Run it
python scripts/verify_login_lifecycle.py
Exit code 0 means every check held. Read the transcript either way: a check that fails still tells you which behaviour changed, which is the part a pass count throws away.
The states, in the order the design names them
| state | setup | what the user should see |
|---|---|---|
| kept | seed the store, then a bare read |
owned store -> N cookies, already kept; no browser opened, (logged in) |
| copy | not kept, --cookies-from-browser, no grant |
refusal naming the per-session approval, exit 3, no network |
| copy, granted | grant, then the same read | copied for this session only, not kept |
| signin | not kept, nothing to copy | reads anonymously, then a login wall names both commands |
| kill | kept, then login kill |
removed from the store; browser's own cookies explicitly left alone |
Checking it can fail
The script prints a FAIL line and exits non-zero if any check breaks, so it is usable as a gate and not only as a demo. To confirm that, break one thing on purpose:
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.
- 17d ago First seen · 71 lines · 91 tokens per session scan A 89ac0c50d195
verify-login-lifecycle is a skill published in the GitHub repository capad-xyz/searchts (2 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 732 once invoked, about $0.0004 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 2026-10-13.
Other skills, from other repositories
test-writer
Expert test writer for unit, component, E2E, and integration tests. Writes only high-value tests — branching, side effects, transactions, corner cases. Use for TDD or filling coverage gaps. Never writes tests for constants, single pass-throughs, or thin wrappers. Adapts to the project's test framework and conventions.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
tmux-real-user-testing
A real-user test workflow for Qwen Code's terminal interface, using tmux to drive the program and capture readable screen snapshots. tmux is a tool for running and observing terminal sessions.
agent-reproduce-align
Use after a Codex or Claude Code feature has been implemented in Qwen Code to run the selected reference agent and Qwen Code under the same scenario, capture HTTP and terminal traces, compare request bodies, tool/function schemas, outputs, and iterate until the reproduced behavior is close enough.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.