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 schub-tech/llm-ideation-wiki --skill onboardinggit clone --depth 1 https://github.com/schub-tech/llm-ideation-wikiWrote 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/schub-tech/llm-ideation-wiki/onboarding)<a href="https://agentmods.dev/skills/schub-tech/llm-ideation-wiki/onboarding"><img src="https://agentmods.dev/badge/skills/schub-tech/llm-ideation-wiki/onboarding.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 | $0.00043 | $0.00558 |
| Opus 5 | $0.00022 | $0.00279 |
| Sonnet 5 | $0.00009 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade C, and why
onboarding 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 8d 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.
3. If `ntn` is missing, tell the user the Notion CLI is required. Ask before installing external software, then install with the official command `curl -fsSL https://ntn.dev | bash` when approved. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. If `ntn` is missing, tell the user the Notion CLI is required. Ask before installing external software, then install with the official command `curl -fsSL https://ntn.dev | bash` when approved. What it actually says
Set up the repo as a Notion-backed idea wiki. Do infrastructure only; do not create ideas.
Ask first.
If the user has not already provided it, ask for the Notion page URL to use as the wiki root.
Do not proceed until you have the root page URL.
Set up Notion.
- Read
README.md,AGENTS.md,docs/agent/notion-contract.md, andnotion.config.jsonif it exists. - Check whether
ntnexists withcommand -v ntnorntn --version. - If
ntnis missing, tell the user the Notion CLI is required. Ask before installing external software, then install with the official commandcurl -fsSL https://ntn.dev | bashwhen approved. - Run
ntn doctor. - If the CLI is not authenticated, run
ntn login. This should open the user's browser; ask the user to complete the browser approval and confirm the verification code. - If the environment is headless and
ntn loginprints a URL and poll command, show the URL/code to the user, then run the printed poll command after they approve in the browser. - Re-run
ntn doctorafter login. - Extract the page ID from the Notion URL and store it as the compact ID in
notion.config.json. - For a new wiki root, reset
pagesinnotion.config.jsonbefore seeding so old page IDs are not reused. - Set
modetonotion-cli, keepversion: 1, and storeroot_url,root_page_id,root_title, androot_emoji. - Run
scripts/notion_wiki.py seed --refresh-existingto createRaw,Shared,Wiki, andTemplates.
Finish.
- Run the ritual (
AGENTS.md§ Mechanics), plusscripts/notion_wiki.py ls. - Tell the user setup is complete and the next step is
/founder-profile. After that, use/new-ideato create the first idea.
Rules.
- Do not create idea pages during onboarding.
- If the root page title or icon cannot be read, default to
LLM Wikiand🧠. - The agent can start browser login, but the user must approve Notion access themselves.
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.
- 8d ago First seen · 38 lines · 43 tokens per session scan C fb64a5abf3cb
onboarding is a skill published in the GitHub repository schub-tech/llm-ideation-wiki (11 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 558 once invoked, about $0.0002 per session on Opus 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
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
batch-all-issues
Resolve every open issue one at a time: fact-check each with web research, close the ones that need no action, and run the goal-pr skill to fix, review, and merge the ones that do — repeating until no actionable issues remain.
slack-tools
Slack workspace management and automation specialist.
create-issue-with-websearch
Create a GitHub issue from a vague idea by thoroughly researching the topic on the web to sharpen the specification before filing.