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 tonydzi/second-brain-starter-kit --skill follower-onboardgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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/tonydzi/second-brain-starter-kit/follower-onboard)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/follower-onboard"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/follower-onboard.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 | $0.00099 | $0.03179 |
| Opus 5 | $0.00049 | $0.01589 |
| Sonnet 5 | $0.00020 | $0.00636 |
| Haiku 4.5 | $0.00010 | $0.00318 |
Grade A, and why
follower-onboard 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 7d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/follower-onboard — connect a follower-consumer (v1 data-only)
🧒 When reporting to the operator, end with a child-simple "In plain words" recap (memory
eli5-always). Reports TO the operator only — never inside the package files.
Single command to build + deliver a follower onboarding package. Drives the tested generator over the master template. Full state + every decision + the gotchas = memory [[machine-migration]] (READ it first each run — the project is live, this is where the hard-won traps live).
The v1 shape (decided 2026-06-24, do NOT re-litigate)
A follower = a reading room for data. The hub SYNCS DATA the follower READS; it NEVER pushes executable code.
| Folder | Follower-side type | Why |
|---|---|---|
Owner-Knowledge (vault, Bible) |
Receive-Only | reads the Second Brain |
claude-home (CLAUDE.md + commands) |
Receive-Only | the canon — whitelist .stignore blocks hooks/secrets/scripts |
claude-memory |
Receive-Only | "one shared memory" |
claude-imports |
Receive-Only | scripts (code only, big data ignored) |
claude-skills |
Receive-Only | uses all skills |
_machine-bus |
sendreceive (tiny, versioned) | the ONLY 2-way folder (mailbox) |
ALL data folders RECEIVE-ONLY (skills too). A sendreceive skills/vault share from a follower is a DATA-LOSS VECTOR — a follower's empty folder can propagate deletions cluster-wide (it wiped the hub's skills 2026-06-24). Contributions (skills + vault notes) go via the moderated _transit channel (vault-proposals/<name>/, canon-proposals/), hub folds them in — NOT direct sync.
NO hub-pushed hooks / settings.json in v1. A follower's stock Claude CORRECTLY refuses to let a remote machine push executable hooks/** (a backdoor); a pasted "authorization" is not sufficient proof. So the hub pushes zero remote-exec. The inbox-robot is the one exception BY KIND — MANDATORY on every machine (operator's order, 2026-06-25), but installed LOCALLY by the follower's own Claude with the operator's explicit consent. A local scheduled task the operator sets up ≠ a hub push, so it is NOT the backdoor the no-hooks rule blocks. It rides the _machine-bus (the only sendreceive folder). Install via bootstrap STEP 8/9 (INBOX-ROBOT-LAUNCHER.md in _transit). The v1/v2 axis is about DATA-scope (v2 adds the Telegram-leads connector), NOT about the robot — the robot is baseline-mandatory, orthogonal to v1/v2.
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.
- 7d ago First seen · 104 lines · 99 tokens per session scan A b904567de13e
follower-onboard is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 8d ago), licensed MIT. It adds 99 tokens to every session and 3,179 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…
wiki-mode
Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing.…
wiki-cli
Detect and use the official Obsidian command-line interface for read-only vault access; use for wiki-cli, Obsidian CLI, Obsidian read, Obsidian search, vault transport, which transport, transport detection, backlinks, tags, or Obsidian command line. Mutations always go through the claude-obsidian transaction core.