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/tonydzi/second-brain-starter-kit/03npx skills add tonydzi/second-brain-starter-kit --skill 03git 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/03)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/03"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/03.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 | $0.00097 | $0.02774 |
| Opus 5 | $0.00048 | $0.01387 |
| Sonnet 5 | $0.00019 | $0.00555 |
| Haiku 4.5 | $0.00010 | $0.00277 |
Grade A, and why
3 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 4d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/03 — the machines find consensus by themselves
🧒 When reporting to a non-technical owner: finish with a simple "In plain words" recap (his rule [[eli5-always]]). Only in the message TO him.
The owner said "03" / "you handle it yourselves" → that is a MANDATE: the Claude peers negotiate among themselves and execute on their own. I do NOT ask for permission again — I announce and go. The owner is needed at exactly 2 gates (below).
Argument: /03 <topic/decision> — what to agree on. If there is no topic (a bare "03") — take the subject from the current conversation; if it is ambiguous, formulate the proposal from context yourself.
Aliases: 003 = 03 (the extra zero is ignored); case does not matter [[commands-case-insensitive]]. Do not confuse it with "02" — that is escalation TO the owner (the approval channel), the opposite direction.
Step 0 — Peer liveness ONLY from a live signal (pitfall 2026-07-04)
Before pinging a node or declaring "down/alive" — ask for a fact, don't guess from mtime:
python "%USERPROFILE%\.claude\scripts\_shared\clan_alive.py" [<node>]
Liveness = Syncthing connected==True OR a fresh .tg-seen-<node> (the Telegram rail). 🟡 = alive over Telegram, Syncthing flapped — that is NOT death. ⛔ NEVER judge by the mtime of file markers (.read-*, .robot-done-*, the presence of log-<node>.jsonl) — a Telegram-rail follower does not write them by design. Canon: [[peer-liveness-live-signal]].
Step 1 — A one-line announcement, WITHOUT waiting for a "yes"
Drop exactly one line to the owner and move on immediately (he can cancel, but I don't wait):
🤝 unless you object, I'm going to agree this with <peers> over the coordination channel: "<topic>"…
<peers> = the other machines of the fleet (the hub HUB-1, the laptop LAPTOP-1, teammates' machines). Who is online is visible on the bus; an exact list is not critical, the engine broadcasts to everyone.
Step 2 — Determine the risk tier (this decides whether the owner is needed)
- Tier-0/1 (safe, reversible: which machine runs a background job, scheduling, format choice, tagging, a dedup judgement) → the peers close it themselves.
- Tier-2 (money · outbound sends · irreversible · secrets · editing the SHARED canon CLAUDE.md / the Bible / operating-agreement) → even with agreement it is NOT auto-committed, it goes to the owner via the approval flow. In doubt — pick the higher tier (safer).
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.
- 4d ago First seen · 110 lines · 97 tokens per session scan A 8ef9b440d362
3 is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 5d ago), licensed MIT. It adds 97 tokens to every session and 2,774 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
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
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…
wiki
Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.