Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add wenlan-app/wenlan --skill run-wenlan-appgit clone --depth 1 https://github.com/wenlan-app/wenlanWrote 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/wenlan-app/wenlan/run-wenlan-app)<a href="https://agentmods.dev/skills/wenlan-app/wenlan/run-wenlan-app"><img src="https://agentmods.dev/badge/skills/wenlan-app/wenlan/run-wenlan-app/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/wenlan-app/wenlan/run-wenlan-app"><img src="https://agentmods.dev/badge/skills/wenlan-app/wenlan/run-wenlan-app.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 | $0.00071 | $0.05089 |
| Opus 5.5 | $0.00028 | $0.02036 |
| Sonnet 5.5 | $0.00014 | $0.01018 |
| Haiku 4.5 | $0.00007 | $0.00509 |
Grade A, and why
run-wenlan-app 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run wenlan-app (dev)
Tauri 2 desktop app (Rust app/ + React/Vite frontend on :1420). Drive it
with .claude/skills/run-wenlan-app/driver.sh — all paths below are relative
to the unit root (repo or worktree root).
Prerequisites, both Run sections, Gotchas, and Troubleshooting below are
macOS only (driver.sh, vite, ScreenCaptureKit). On Windows the webview is
WebView2 and the recipe is different — jump to
Windows (WebView2).
A debug build refuses to start without a complete isolated runtime identity
(validate_debug_runtime_isolation in app/src/lib.rs), so launch takes the
worktree-scoped config from scripts/dev-runtime.sh and starts its own
daemon on the worktree port. The user's live wenlan-server on :7878 is
never the daemon under test and must never be killed; stop only ends the
daemon this worktree recorded.
Prerequisites
pnpm installdone in the unit root (worktrees start withoutnode_modules).- No sibling checkout needed: the monorepo checkout is the backend, and
scripts/resolve-backend-dir.shprobes the repo root first (an explicitWENLAN_BACKEND_DIRoverrides it; a sibling checkout is only a legacy fallback). The driver defaultsCARGO_TARGET_DIRto the main checkout (a warm cargo cache) viagit rev-parse --git-common-dir, so worktrees work out of the box. - Terminal needs macOS Screen Recording permission (for
shot).
Run (agent path)
.claude/skills/run-wenlan-app/driver.sh build # sidecars + cargo build (decoupled from tauri dev)
.claude/skills/run-wenlan-app/driver.sh launch # isolated daemon + vite up + launch target/debug/wenlan-app directly → "APP UP"
.claude/skills/run-wenlan-app/driver.sh shot /tmp/shot.png # window PNG, works while occluded
.claude/skills/run-wenlan-app/driver.sh stop # kills only the dev app, vite, and this worktree's daemon; never :7878
Logs land in $TMPDIR/wenlan-app.log and $TMPDIR/wenlan-vite.log.
Look at the screenshot after shot — a blank frame means the frontend
did not load.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 353 lines · 71 tokens per session scan A 76eabd53f519
run-wenlan-app is a skill published in the GitHub repository wenlan-app/wenlan (82 stars, last pushed yesterday), licensed Apache-2.0. It adds 71 tokens to every session and 5,089 once invoked, about $0.0003 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 2026-10-11.
Other skills, from other repositories
verify
Drive/evidence recipe for verifying wenlan changes at their real surfaces (daemon HTTP, CLI, MCP stdio). The handle file the built-in verify protocol expects; launch primitives live in the run-wenlan skill, deeper machinery (mutation audit, behavior trace, weekly sweep) in the prove skill.
prove
Per-surface verification loops for wenlan — daemon, cli, mcp, plugin, suite strength (mutation), behavior trace, weekly sweep. Routes to scripts; every check records evidence via attest. Deeper than the built-in verify skill — use prove for mutation audits, behavior tracing, and the weekly sweep; built-in /verify…
run-wenlan-app
Build, launch, screenshot, and drive the wenlan-app Tauri desktop app in dev mode on macOS (WKWebView) or Windows (WebView2). Use when asked to run or start the app, verify a UI change in the real running app (not just tests), or take a screenshot of it.
help
Show a one-screen Codex reference for the Wenlan plugin. Use when the user asks for Wenlan help, command list, invokes /help, or explicitly asks about import progress.
run-wenlan
Build, launch, and stop the wenlan daemon (wenlan-server) for local dev and verification. Use when asked to run or restart the daemon, or before driving any surface (HTTP, CLI, MCP) against a live instance.
setup
Frictionless Wenlan setup for Codex. Detects a missing local runtime, installs or repairs it, and verifies the plugin to MCP to local runtime round-trip. Run when the user says "set up wenlan", "is wenlan working", or "fix wenlan".