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 helpgit 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/help)<a href="https://agentmods.dev/skills/wenlan-app/wenlan/help"><img src="https://agentmods.dev/badge/skills/wenlan-app/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/wenlan-app/wenlan/help"><img src="https://agentmods.dev/badge/skills/wenlan-app/wenlan/help.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 | $0.00073 | $0.01023 |
| Opus 5.5 | $0.00029 | $0.00409 |
| Sonnet 5.5 | $0.00015 | $0.00205 |
| Haiku 4.5 | $0.00007 | $0.00102 |
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 3d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/help
Print the Wenlan plugin reference card. The default help path is read-only and never calls a tool.
How to invoke
When triggered, output the block below verbatim. No editing, no
abbreviating, no embellishing. The user is asking for the menu. The one
exception: skip the <!-- ... --> comment lines inside the block; they mark
the generated verb list and are not part of the card.
Wenlan plugin — daily verbs
<!-- verbs:start -->
<!-- generated from the Claude help card by scripts/gen-codex-plugin.mjs; edit plugin/skills/verbs.json -->
/setup set up or repair Wenlan (installs the local runtime)
/brief [topic] load the Brief for the current Space (optional; not a boot step)
/capture <x> save one durable memory in flow
/recall <q> search local memory
/lint [deep|repair] [scope] diagnose, or resolve all findings safely
/distill [t] synthesize or refresh source-backed pages for the active Space
/pages [q] browse and open distilled pages
/curate <surface> deep audit of captures, revisions or refinements
/forget <id> delete one memory by ID, after confirmation
/handoff end-of-session debrief: captures, session log, Brief update
/help one-screen quick reference
<!-- verbs:end -->
Import progress: ask explicitly; Wenlan checks `list_pending_imports` on demand.
Daily flow (~1 min overhead per session):
1. /setup → once after install, or when Wenlan looks broken
2. /brief → resume a project or ask to catch up
3. work normally → Codex proactively /captures durable facts
4. /recall X → as needed for lookups
5. /handoff → ~30 s, narrative session log + captures
Where your data lives (under ~/.wenlan/):
~/.wenlan/pages/ wiki pages distilled from your memories (md)
~/.wenlan/sessions/ session logs by date (md)
~/.wenlan/sessions/_status/ human receipts projected from Space Briefs
Memories and the graph live in a local database; location in docs/setup-and-data.md.
View it without a GUI:
wenlan pages list recent pages
wenlan pages "<query>" --print read one page and its sources in the terminal
open ~/.wenlan/ browse in Finder
code ~/.wenlan/ open in VS Code
ln -s ~/.wenlan/pages ~/Vault/wenlan # symlink into Obsidian for graph view
Three classes of artifact:
- memories: granular, queryable, live in DB only (confirmed = stays in DB)
- pages: synthesized wikis, DB + ~/.wenlan/pages/*.md projection
- sessions: chronological narrative, ~/.wenlan/sessions/*.md only
The local runtime must run at 127.0.0.1:7878. If it or the MCP bridge is down, run /setup.
Models and keys do not enable background inference by themselves:
wenlan steep status show Everyday + Synthesis as off, ready, or paused
wenlan steep configure --everyday <source> --synthesis <source>
review the exact mapping, disclosure, and confirm
wenlan steep disable turn model-backed background work off
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.
- 3d ago Changed · +32 lines · +34 tokens per session 8e565f56ad09
- 4d ago First seen · 68 lines · 39 tokens per session scan A b494c6063cea
help is a skill published in the GitHub repository wenlan-app/wenlan (82 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 1,023 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
forget
Delete a Wenlan memory by exact id from Codex. Destructive and confirmation gated. Invoked as /forget .
pages
List or open distilled Wenlan pages from Codex by delegating to the local wenlan pages CLI. Invoked as /pages [query].
recall
Search Wenlan's local memory from Codex by query. Targeted lookup, not session orientation. Invoked as /recall .
brief
Read the current Space-owned project Brief from Wenlan for Codex. With an optional topic, appends separately labeled related context from the same Space. Invoked as /brief [topic] when resuming work or asking to catch up.
capture
Save a durable memory to Wenlan from Codex. Use proactively when the user states a preference, makes a decision, corrects you, or shares a durable fact. Invoked as /capture .
handoff
End a Codex work session. Stores durable captures, writes a narrative session log, and automatically applies typed item-level deltas to the current Space Brief. Invoked as /handoff.