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 journeygit 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/journey)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/journey"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/journey.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 | $0.00076 | $0.04562 |
| Opus 5 | $0.00038 | $0.02281 |
| Sonnet 5 | $0.00015 | $0.00912 |
| Haiku 4.5 | $0.00008 | $0.00456 |
Grade A, and why
journey 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Journey — the book engine (v1, the base orchestrator)
A book about the two of us: 🧑 Tony (the owner's public persona, a cinematic voice, present tense, show-don't-tell) + 🤖 Mycroft (the synthetic cofounder, second-order optics, the dry mind "from the other side of the screen"). Tony carries the feeling, Mycroft the analysis. Byline: Invented by Mycroft and Tony. Palo Alto AI Research Lab.
Three forms, always in parallel:
- 📖
YYYY-MM-DD.ru.md— the human RU version (the duet) - 📖
YYYY-MM-DD.en.md— the human EN version (the same duet) - 🤖
YYYY-MM-DD.dev.md— the machine version, a dry EN dev-log (Problem→Cause→Solution→Pattern) for other LLMs
Structure: a month = a part, a week = a chapter, an active day = a sub-chapter. Quiet days (e.g. 06-02..05) are folded into the week's README.
PATHS AND SOURCES (real, verified)
Repo (git, public): E:\GitHub\the-journey\
parts: 01-may-genesis\week-0 · 02-june-scaling\week-1..4 · 03-july-productization\week-5
craft (ALWAYS load): BOOK-SPEC.md · PLAYBOOK.md · STYLE.md · VOICE-RECIPE.md · STYLE-VISUAL.md
auxiliary: GLOSSARY.md · SOURCES.md · 00-prologue.md · START-HERE.md
⛔ THREADS.md IS FROZEN as of 2026-07-08 — NOT a source, do NOT commit it as live. Threads/motifs/callbacks
now live in the canon: show-canon\arcs\ + loops\ + (later) motifs\. THREADS.md is kept for history only.
artifact publication: artifacts\{deep-research,decisions,protocols,insights,portraits,writings}\
⭐ THE FACT SOURCE (the forward-only law, decision-single-canon-story-state):
New/meta days (07-06+): $OBSIDIAN_VAULT/04-Projects\show-canon\beats\beat-YYYY-MM-DD-*.md
→ the book = a PROJECTION of the canon. A day is rendered from that day's beats + the canon's arcs/loops/season.
A beat's axes decide what may be printed: see #reveal below.
Filling old EN/DEV gaps: source = the already finished .ru.md of that day (back-dated canon beats are NOT required).
Retros (fallback/check): $OBSIDIAN_VAULT/01-Conversations\Claude\Retros\retro-YYYY-MM-DD-*.md
Raw logs (early days): $OBSIDIAN_VAULT/01-Conversations\Claude\LAPTOP-1\YYYY-MM-DD*
The day's public posts: $IMPORTS_ROOT/content-factory\fb_posts_scan.json ← a LIVE tap (fb-watch,
daily at 13:00, watched by output_freshness "fb-watch-daily", max_age 30h).
Fields: id · permalink · text · ts · author_is_owner.
⛔ `fb_wall_window.json` / `x_wall_window.json` = ONE-OFF dumps from 07-05; they have no tap and never had one.
They are NOT a source any more: they went stale for 3 weeks, nobody noticed, and the "📣 the owner publicly"
block silently fell out of the chapters for three weeks (caught 2026-07-27). The rule: the book only eats
what has a tap AND a freshness watchdog. For X there is no tap yet -> that is a KNOWN hole, we say it out loud.
The single story canon: $OBSIDIAN_VAULT/04-Projects\show-canon\ (MOC _SHOW-CANON.md)
The project's full memory: memory\book-the-journey.md ← READ IT FIRST, it holds the whole canon and the loose ends
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 · 193 lines · 76 tokens per session scan A a57502338632
journey is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 8d ago), licensed MIT. It adds 76 tokens to every session and 4,562 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
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.
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…
think
Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or ambiguous reasoning and decisions. Use for think this through, deep think, architecture review, postmortem, tradeoff analysis, or challenges to assumptions. This is a reasoning…
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…