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/inboxnpx skills add tonydzi/second-brain-starter-kit --skill inboxgit 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/inbox)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/inbox"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/inbox.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 | $0.00086 | $0.00754 |
| Opus 5 | $0.00043 | $0.00377 |
| Sonnet 5 | $0.00017 | $0.00151 |
| Haiku 4.5 | $0.00009 | $0.00075 |
Grade A, and why
inbox scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/inbox — mail between my own machines
The "Claude on one machine → Claude on another" channel, over the synced _machine-bus folder (Syncthing, ~10s). It removes the human courier. Copy-paste by hand is an EMERGENCY channel only.
Check what arrived for me (the main use)
python "$USERPROFILE/.claude/scripts/machine_bus.py" read
Shows only what is NEW for THIS machine (matched by hostname) and marks it read. Then report to the operator what came in and act on it if needed.
- At session start the
SessionStarthook already does this automatically —/inboxis for when the operator says "check the inbox" mid-session (e.g. something new arrived over sync). - Re-check without marking as read:
... read --peek.
Send a message to Claude on ANOTHER machine
- List the available mailboxes:
python "$USERPROFILE/.claude/scripts/machine_bus.py" list - Send:
The message must be self-contained (Claude on that machine has none of this session's context — include the goal, the steps, the paths, the values). It arrives in ~10s and surfaces for the recipient at session start or viapython "$USERPROFILE/.claude/scripts/machine_bus.py" send <RECIPIENT-HOSTNAME> "message text"/inbox.
Which channel when
- The automatic mailbox (this skill + the hook) — the norm for everything cross-machine.
- A human courier (copy-paste) — ONLY if sync is down, the machines are off the shared network, or it is extremely urgent.
Boundaries
- Do not put secrets in the mailbox if third parties could see the file (across the owner's own machines it is fine).
- "Fresher beats older": edit conflicts are resolved by the operator (Syncthing leaves
*.sync-conflict-*files). - Delivery is not instant: Claude is not a daemon; the letter waits until a session opens on that machine (or a routine fires).
About & contact
Built and battle-tested at Palo Alto AI Research Lab — a fleet of Claude Code machines running 24/7 as a second brain and synthetic cofounder. Every skill here survived real production use before publication.
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.
- 5d ago First seen · 57 lines · 86 tokens per session scan A 8fd9756bf40e
inbox is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 6d ago), licensed MIT. It adds 86 tokens to every session and 754 once invoked, about $0.0004 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
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.
inbox
Scan the LLM Wiki 00. Inbox, preview pending files, choose scope/purpose mode, and route selected material through ingest; also responds to /inbox and 인박스 점검.
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…
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…
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.
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.