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 agentmods add skills/7xuanlu/wenlan/curatenpx skills add 7xuanlu/wenlan --skill curategit 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/curate)<a href="https://agentmods.dev/skills/7xuanlu/wenlan/curate"><img src="https://agentmods.dev/badge/skills/7xuanlu/wenlan/curate.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.01254 |
| Opus 5 | $0.00028 | $0.00627 |
| Sonnet 5 | $0.00011 | $0.00251 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
curate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/curate
Power-user audit of Wenlan pending surfaces. Daily flow should stay light:
/brief shows the top pending revisions and /handoff previews recent pending
captures. Use /curate only when the user asks to walk the queue.
Safety protocol
Perform no mutation until the user replies. Ambiguous replies do not mutate. Cancellation, no reply, or unclear syntax is a no-op.
Render at most four items at a time. Number every item. Ask for explicit action syntax:
1 accept
2 dismiss
3 skip
4 edit: <replacement text>
Do not rely on hidden pagination state across turns. After applying a batch, re-list before showing another batch.
/curate revisions
Use the local CLI, not MCP, because revision actions must key on the exact
revision_source_id.
Resolve wenlan:
if command -v wenlan >/dev/null 2>&1; then
W="$(command -v wenlan)"
elif [ -x "$HOME/.wenlan/bin/wenlan" ]; then
W="$HOME/.wenlan/bin/wenlan"
else
echo "wenlan not found"
exit 127
fi
"$W" --format json curate
If wenlan is missing, tell the user to run /setup.
The JSON array contains:
revision_source_id: staged revision id; action key for accept/dismiss.target_source_id: original memory id; context only.content: revised text.source_agent: proposer.original: current text when available.diff: ready-made OLD/NEW preview when available.
Render up to four revisions:
Pending revisions:
1. revision_source_id: <rev_id>
target: <target_source_id>
proposed: "<content>"
diff:
<diff or "(original unavailable)">
Reply with: 1 accept, 1 dismiss, 1 skip
Apply only explicit actions:
"$W" curate accept <revision_source_id>
"$W" curate dismiss <revision_source_id>
accept replaces the original memory with that named revision. dismiss
unstages the false revision link and keeps both memories as independent rows.
skip does nothing.
/curate captures
If the user names a space, parse space:<name> and pass it to
mcp__wenlan__list_pending. Otherwise leave space off so the audit covers
all pending captures.
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.
- 6d ago First seen · 159 lines · 55 tokens per session scan A 28b3809751ba
curate is a skill published in the GitHub repository 7xuanlu/wenlan (63 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,254 once invoked, about $0.0003 per session on Opus 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
capture-task
Capture a new task — create a draft or pending Task record from a rough idea or detailed spec. Use when asked to "add a task", "log a bug", "create a task", or "add to backlog".
refine-backlog
Refine the backlog — screen drafts, remove duplicates, fill in missing details, classify, link, and move to pending.
implement-task
Pick up and work on a binder Task — investigate bugs, discuss open questions, design solutions, write tests, or implement code. Use when asked to "work on", "pick up", "implement", or "fix" a task.
project-context-loader
Load relevant memory, decisions and contacts for the current project at the start of a session.
memtrace-fleet-first
Coordinate fleets of coding agents sharing one repo+branch: publish typed intents, classify edit episodes, and resolve conflicts before they collide. Use FIRST when multiple agents work the same repo+branch, before reading/planning/editing, when joining a fleet or handing work off, and when the user says two agents…
obsidian-kanban
Create and maintain Obsidian Kanban boards stored in Markdown, with a GTD-friendly workflow for capturing tasks, adding cards, organizing lists, and maintaining task details such as inline tags, Kanban date and time tokens, linked-note priority metadata, and subtasks. Use when working with Obsidian Kanban board files…