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 tobocop2/lilbee --skill lilbee-mcp-wikigit clone --depth 1 https://github.com/tobocop2/lilbeeWrote 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/tobocop2/lilbee/lilbee-mcp-wiki)<a href="https://agentmods.dev/skills/tobocop2/lilbee/lilbee-mcp-wiki"><img src="https://agentmods.dev/badge/skills/tobocop2/lilbee/lilbee-mcp-wiki/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/tobocop2/lilbee/lilbee-mcp-wiki"><img src="https://agentmods.dev/badge/skills/tobocop2/lilbee/lilbee-mcp-wiki.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 | $0.00060 | $0.00835 |
| Opus 5 | $0.00030 | $0.00417 |
| Sonnet 5 | $0.00012 | $0.00167 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade A, and why
lilbee-mcp-wiki 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 11d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
lilbee-mcp-wiki
The wiki layer generates per-concept and per-entity pages with citations from
the indexed library, then lets you query and lint them. It is still rough; treat
it as opt-in, not part of normal answer flow. Skip everything here unless the
user explicitly asks about wiki / synthesis pages, or lilbee_status already
shows a wiki built.
lilbee_wiki_status is the only wiki tool available regardless of the flag; it
reports wiki_enabled with zeroed counts when the wiki is off. Every other wiki
tool is absent from the surface when the server started with the wiki disabled,
and returns {"error": "wiki not enabled"} if the flag is turned off while the
server is running. Enabling the wiki with lilbee_settings_set({"wiki": true})
brings the rest of the tools back on the next server session, not the current
one.
The shared-embedder rule from the parent lilbee-mcp skill still applies: any
LLM-bound wiki op (build, update, synthesize) goes through the
lilbee-worker subagent.
Build / refresh (long, must go through lilbee-worker)
| Tool | Use |
|---|---|
lilbee_wiki_build() |
Generate the full topic / entity wiki from the indexed library. LLM-bound; minutes per source. |
lilbee_wiki_update() |
Refresh the wiki after a sync. Currently a full rebuild. |
lilbee_wiki_synthesize() |
Generate cross-source synthesis pages (concept clusters spanning ≥3 sources). |
lilbee_wiki_prune() |
Archive stale wiki pages whose sources were deleted, and flag pages with mostly-stale citations. |
Read / inspect (inline)
| Tool | Use |
|---|---|
lilbee_wiki_status() |
The wiki_enabled flag, summary/draft/page counts, and lint error and warning counts. |
lilbee_wiki_list() |
Every wiki page with slug, title, type, source count. |
lilbee_wiki_read(slug) |
Read one wiki page's body + frontmatter. |
lilbee_wiki_lint(wiki_source) |
Find orphan pages, stale citations, pending drafts. Pass empty wiki_source to lint all. |
lilbee_wiki_citations(wiki_source) |
Per-section citation coverage for one wiki page. |
lilbee_wiki_citations(source=...) |
Reverse lookup: the wiki pages citing one source document. |
lilbee_wiki_build(dry_run=True) |
Preview the entity candidates a build would cover. No LLM calls, so it runs inline. |
lilbee_wiki_drafts_list() |
Pending drafts with drift, faithfulness, and pairing info. |
lilbee_wiki_drafts_diff(slug) |
Unified diff between a pending draft and the live page. |
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.
- 11d ago First seen · 60 lines · 60 tokens per session scan A 1610504e8d56
lilbee-mcp-wiki is a skill published in the GitHub repository tobocop2/lilbee (53 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 835 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
tiktok-video
A workflow for making vertical short videos for TikTok or Douyin from a written request. It creates a storyboard, voiceover, word-timed karaoke captions, background music, and a 1080×1920 MP4 video.
sentence-transformers
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production…
gog-workspace
Use the gog CLI for Google Workspace tasks across Gmail, Calendar, Drive, Docs, Sheets, Contacts, and related services. Use when the user asks to check email, search Gmail, inspect calendar events, find Drive files, read Docs or Sheets, or manage Google Workspace data through gog.
apple-calendar
Read macOS Calendar events via the icalBuddy CLI and create events via AppleScript (osascript). Use to check the user's calendar, agenda, upcoming events, or add an event on macOS.
apple-reminders
Manage Apple Reminders via the remindctl CLI on macOS — list, add, complete, delete, manage lists.
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.