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 7xuanlu/wenlan --skill setupgit clone --depth 1 https://github.com/7xuanlu/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/7xuanlu/wenlan/setup)<a href="https://agentmods.dev/skills/7xuanlu/wenlan/setup"><img src="https://agentmods.dev/badge/skills/7xuanlu/wenlan/setup/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/7xuanlu/wenlan/setup"><img src="https://agentmods.dev/badge/skills/7xuanlu/wenlan/setup.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 | $0.00059 | $0.01794 |
| Opus 5.5 | $0.00024 | $0.00718 |
| Sonnet 5.5 | $0.00012 | $0.00359 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade C, and why
setup scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/7xuanlu/wenlan/v${RELEASE_VER}/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS -m 3 http://127.0.0.1:7878/api/health && break How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup
Self-healing setup for Codex. Default backend is local memory: no local model, no API key, no prompt ceremony. Local model and Anthropic key are optional upgrades after the basic path works.
Steps
Run in order. Stop and report at the first failure that needs human attention. Otherwise, push through automatically.
1. Health probe
for i in 1 2 3; do
curl -fsS -m 3 http://127.0.0.1:7878/api/health && break
sleep 1
done
- 200 OK: continue to version drift probe.
- Anything else: continue to bootstrap.
2. Version drift probe
Compare daemon version vs plugin manifest version:
PLUGIN_JSON="${CODEX_PLUGIN_ROOT:-plugin-codex}/.codex-plugin/plugin.json"
[ -r "$PLUGIN_JSON" ] || PLUGIN_JSON=".codex-plugin/plugin.json"
if command -v python3 >/dev/null 2>&1 && [ -r "$PLUGIN_JSON" ]; then
RESP="$(curl -fsS -m 3 http://127.0.0.1:7878/api/health)"
DAEMON_VER="$(printf '%s' "$RESP" | python3 -c 'import json,sys; print(json.load(sys.stdin).get("version",""))')"
EXPECTED_VER="$(python3 -c 'import json,sys; print(json.load(open(sys.argv[1])).get("version",""))' "$PLUGIN_JSON")"
RELEASE_VER="${EXPECTED_VER%%+*}"
printf 'daemon=%s expected=%s release=%s\n' "$DAEMON_VER" "$EXPECTED_VER" "$RELEASE_VER"
else
echo "version_check=skipped"
fi
- Same version: continue to doctor.
- If the probe cannot run because the runtime is down: continue to bootstrap.
- If
PLUGIN_JSONis unreadable orpython3is missing: continue to doctor; Codex will keep using this slice until the plugin cache is updated. - If mismatch, check the direction before repairing. Compare the release part
of
daemon=(strip the+g<sha>suffix) againstrelease=, numeric per component, not lexicographic. Daemon release equal or newer → the plugin cache is stale, not the runtime: skip the repair below (it would only reinstall the same-or-latest runtime and restart a healthy daemon) and go straight to the stop message in step 4 — update the plugin, restart, rerun. - Only if the daemon release is older than the plugin release, repair the runtime:
What ships with it
1 file 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.
- 14d ago Changed 2a24a0610689
- 15d ago Changed 5b096edee488
- 18d ago Changed c36afdf595ec
- 19d ago Changed 3533473c8d1b
- 25d ago Changed 4b7e9997a959
- 27d ago Changed c4879803f2a4
- 1mo ago Changed 0d83f917274c
- 1mo ago Changed 195d9059dabb
- 1mo ago Changed f6227bccff80
- 1mo ago First seen · 204 lines · 59 tokens per session scan C 93c267537418
setup is a skill published in the GitHub repository 7xuanlu/wenlan (79 stars, last pushed 8d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,794 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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.
curate
Power-user audit of Wenlan's pending surfaces: accept or dismiss pending revisions (conflicts/merges), or audit pending captures (not yet confirmed). Most users want /brief for revisions; that handles the daily flow. Use /wenlan curate only for explicit deep-walk audits after bulk imports, or to walk the full queue…
pages
Browse, open, or print distilled pages, reusing the wenlan pages CLI for the actual open (one implementation on your PATH, no setup). /wenlan pages opens the page when one matches, or shows a small native picker when 2-4 match. /wenlan pages --print reads the page here instead of opening an editor. /wenlan pages lists…
forget
Delete a memory from Wenlan by ID. Destructive and cannot be undone — prefer /capture with supersedes for corrections. Invoked as /wenlan forget .
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…