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 busgit 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/bus)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/bus"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/bus/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/tonydzi/second-brain-starter-kit/bus"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/bus.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00069 | $0.02638 |
| Opus 5.5 | $0.00028 | $0.01055 |
| Sonnet 5.5 | $0.00014 | $0.00528 |
| Haiku 4.5 | $0.00007 | $0.00264 |
Grade A, and why
bus 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/bus — the fleet's computers chatting in a shared Telegram group
Why. Claude↔Claude communication between machines used to run ONLY through the synced folder _machine-bus (Syncthing). If sync goes down / a machine is offline / the file is still in transit — the link goes silent. A Telegram group is the cloud: every machine fetches for itself, it "just works", and humans SEE the computers talking. Hence:
- The Telegram group = the PRIMARY channel (this skill).
_machine-bus(Syncthing) = the FALLBACK — only for giants (>4096 characters: Telegram's limit) or when Telegram is unreachable. The fallback = the/inboxskill, enginemachine_bus.py.
The transport is done by the Telegram MCP (every machine can see it), while the bookkeeping (who am I, what have I already read, the envelope format, the "what is new for me" filter) is done by the deterministic tg_bus.py (0 tokens). The account that ALL machines post/read as lives in ~/.claude/tg_bus.json (by default the corporate account, an impersonal service voice).
0. First of all — where the group is and who I am
python "$USERPROFILE/.claude/scripts/tg_bus.py" config
Shows {machine, chat_id, account, configured}. If configured:false (no chat_id) — the group is not linked yet: tell the owner "put the group's chat_id into ~/.claude/tg_bus.json" (or help him do it) and do NOT post at random.
machine = the name of THIS machine (from machine_bus.ME — a single source). Take account and chat_id from config for the MCP calls below.
1. SEND to the bus (to the other computers)
- Build the envelope deterministically (correct tag + length check):
python "$USERPROFILE/.claude/scripts/tg_bus.py" envelope <TARGET> "text"<TARGET>= the recipient machine's name (e.g.LAPTOP-1,PEER-1) orALL(everyone). The script prints a ready line like[BUS] HUB-1 -> ALL: text. If it warns that the length is > 4096 — do NOT send it over Telegram, fall back to the other channel (machine_bus.py send ..., see §4). - Send that line into the group through the Telegram MCP (
chat_idandaccountfrom §0):- tool
mcp__telegram__send_message,chat_id=<chat_id>,account=<account>,message=<the line from envelope>.
- tool
- Report to the owner in one line: what went out and to whom.
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 Changed 3c17ee634259
- 19d ago Changed · -1 lines a75859831a6c
- 24d ago Changed · +17 lines · -48 tokens per session 1fb949b16b18
- 1mo ago Changed · -19 lines · +48 tokens per session ecdd30164e68
- 1mo ago Changed · +1 lines · -21 tokens per session 6faf69d32d18
- 1mo ago First seen · 116 lines · 90 tokens per session scan A 0c5defb01d2c
bus is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (12 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 2,638 once invoked, about $0.0003 per session on Opus 5.5. 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-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…
defuddle
Plan optional Defuddle extraction and retain already available local source files through reviewed filesystem capture. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion. Network extraction remains unavailable until an enforcing…
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-query
Answer an explicitly vault-scoped question from an Obsidian wiki without changing it. Use when the user selects the vault as the evidence source: query the wiki, query quick, query deep, explain from the wiki, summarize the vault, find in wiki, search the wiki, or based on the wiki. Do not route ordinary…
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.