Borrowing it
Nothing to install: this file belongs to advenimus/conduit-desktop. 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/advenimus/conduit-desktop/main/.claude/skills/verify/SKILL.mdgit clone --depth 1 https://github.com/advenimus/conduit-desktopWrote 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/advenimus/conduit-desktop/verify)<a href="https://agentmods.dev/skills/advenimus/conduit-desktop/verify"><img src="https://agentmods.dev/badge/skills/advenimus/conduit-desktop/verify/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/advenimus/conduit-desktop/verify"><img src="https://agentmods.dev/badge/skills/advenimus/conduit-desktop/verify.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 | $0.00000 | $0.06888 |
| Opus 5.5 | $0.00000 | $0.02755 |
| Sonnet 5.5 | $0.00000 | $0.01378 |
| Haiku 4.5 | $0.00000 | $0.00689 |
Grade A, and why
verify scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| appwrite phase fails, or the API does not answer | Stack never set up, half-started, or short of memory | If the message names a missing `conduit-dev.env`, run `npm run appwrite:setup`. Check `curl -s http://localhost: How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/verify: all live suites
Runs npm run verify. The harness in scripts/verify/ builds the app, launches real Electron
devices side by side, drives them like a user (and over MCP), checks the server state in the local
Appwrite, and cleans up after itself. You can run it start to finish without asking the user for
anything. The harness reference is scripts/verify/README.md.
Run every suite only when the user asks for it or for a release candidate. For any other change, run only the suite that covers it, with its skill below; they add per-scenario detail and suite-specific troubleshooting:
| Skill | Suites | Command |
|---|---|---|
verify-sync (.claude/skills/verify-sync/SKILL.md) |
sync |
npm run verify:sync |
verify-mcp (.claude/skills/verify-mcp/SKILL.md) |
mcp |
npm run verify:mcp |
verify-ownership (.claude/skills/verify-ownership/SKILL.md) |
ownership |
npm run verify:ownership |
verify-data (.claude/skills/verify-data/SKILL.md) |
backup, copies, lifecycle, password, resilience |
npm run verify:data, or node scripts/verify/run.mjs <suite> |
Smoke has no skill of its own (node scripts/verify/run.mjs smoke).
What it proves
smoke (harness health)
two-devices: a Free user creates a vault in the shared cloud folder; a second device in local mode shows the vault hub.ipc-and-mcp: in local mode an entry is created, renamed and deleted, and an MCP client on the device sees each change.
sync (personal vault sync and device limits, docs/MULTI_DEVICE_SYNC.md)
free-takeover-server: on Free, device B opens a vault A has open, is offered a take-over, takes it and gets A's data; A is locked out and offered "Use here instead".take-back: A presses "Use here instead" and gets the vault back; B is locked out.pro-merge-and-conflict: on Pro both devices stay open; edits to different fields merge, and a same-field edit and an edit-versus-delete become conflicts that are resolved in the review panel, ending the same on both devices.downgrade-and-upgrade: Pro to Free with two devices open locks out exactly one, with the plan-limit message; back to Pro it reopens with no take-over and the other device stays open.signout-releases-lease: signing out frees the device's server lease within seconds.signed-out-claims: with nobody signed in, the owner claim inside the vault file still drives the take-over and locks A out.legacy-writer: an in-place edit by an old desktop build (0.17) is absorbed with no conflict.file-safety: no-wal,-shmor-journalfile ever appears in the cloud folder during the suite, and every vault file has a WAL header and opens the way iOS 1.0.5 opens it.
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.
- 12d ago Changed 77003fd53093
- 28d ago First seen · 232 lines · 0 tokens per session scan A d0f2315a379f
verify is a skill published in the GitHub repository advenimus/conduit-desktop (19 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,888 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.
Other skills, from other repositories
winui-ui-testing
Write and run automated UI tests for Windows desktop apps (WinUI 3, WPF, WinForms, Win32) with the winapp ui harness: one batch script, assertions, input, file pickers, dialogs, screenshots, locally or in Windows Sandbox. Use when asked for UI tests or to verify a feature end to end.
Appium Mobile Testing
Mobile application testing skill using Appium for iOS and Android, covering device capabilities, selectors, gestures, and cross-platform testing strategies.
browser-qa
Use when validating or debugging a workflow in the embedded browser and you need a reproducible, evidence-first loop.
performance-engineer
Becomes a senior performance engineer who identifies bottlenecks, designs optimization strategies, and conducts load testing using systematic profiling and benchmarking methodology. Use when the user needs performance analysis, load testing, bottleneck identification, latency optimization, or capacity planning. Do NOT…
Desktop Application Testing
Testing desktop applications built with Electron, Tauri, or native frameworks including window management, IPC, tray icons, and auto-update testing.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.