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 helpgit 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/help)<a href="https://agentmods.dev/skills/7xuanlu/wenlan/help"><img src="https://agentmods.dev/badge/skills/7xuanlu/wenlan/help/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/help"><img src="https://agentmods.dev/badge/skills/7xuanlu/wenlan/help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.00592 |
| Opus 5.5 | $0.00016 | $0.00237 |
| Sonnet 5.5 | $0.00008 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
help 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 1mo 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.
What it actually says
/help
Print the Wenlan Codex command card. The default help path is read-only and calls no tools.
Wenlan for Codex
/setup set up or repair the local runtime and MCP bridge
/brief [topic] read the Space Brief; topic adds related context
/capture <x> save one durable memory
/recall <q> search local memory
/lint [deep|repair] [scope] diagnose, or resolve all findings safely
/distill [t] synthesize or refresh source-backed pages
/pages [q] list or open distilled pages in the OS editor
/curate <s> review pending captures or revisions (s = captures|revisions)
/forget <id> delete one memory by exact id after confirmation
/handoff close a session with captures, session log, and a Brief update
/help show this card
Import progress: ask explicitly; Wenlan checks `list_pending_imports` on demand.
Daily flow:
1. /setup once after install, or when Wenlan looks broken
2. /brief when resuming a project or asking to catch up
3. /capture durable decisions, corrections, lessons, or preferences
4. /recall when you need a specific memory
5. /handoff before ending the session
Data lives under ~/.wenlan/:
pages/ source-backed wiki pages
sessions/ narrative session logs
sessions/_status/ human receipts projected from Space Briefs
bin/ installed wenlan and wenlan-mcp binaries
Open pages with /pages. Inspect history with:
git -C ~/.wenlan log --oneline
Optional models and keys do not enable background inference by themselves:
wenlan enrichment status show Everyday + Synthesis as off/ready/paused
wenlan enrichment configure --everyday <source> --synthesis <source>
review the exact mapping, disclosure, and confirm
wenlan enrichment disable turn model-backed background work off
Only when the user explicitly asks whether an import/export is still running,
call mcp__wenlan__list_pending_imports. Never call it during ordinary
/help, /brief, setup, or session-start flows.
If the local runtime or MCP bridge is down, tell the user to run /setup.
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.
- 1mo ago First seen · 65 lines · 39 tokens per session scan A 6dd796bb98e6
help is a skill published in the GitHub repository 7xuanlu/wenlan (79 stars, last pushed 8d ago), licensed Apache-2.0. It adds 39 tokens to every session and 592 once invoked, about $0.0002 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 2026-08-30.
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…