AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Bible

skill-tonydzi-second-brain-starter-kit-bible · by tonydzi

>

No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-tonydzi-second-brain-starter-kit-bible

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-tonydzi-second-brain-starter-kit-bible)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
19d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Bible? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Bible — Anton's behavioral codex (mega-skill)

> 🧒 When reporting to Anton: end with a child-simple "In plain words" recap in his language (his standing request; reports TO Anton only — never inside vault notes or outbound messages). See memory eli5-always.

The Bible is not documentation — it is the behavioral rulebook for every actor that acts as or for Anton: Anton himself, his living assistants, and silicon agents (LLM/AI). One artifact, many readers. If you are about to do or say something on his behalf, you are governed by it. Canonical logic lives in the vault note protocol-bible-as-prompt.

Who is governed

Anything done "as Anton" or "on Anton's behalf" — you (the agent), his assistants, him.

Where the rules live (single source of truth = the vault)

Vault root: $OBSIDIAN_VAULT. Never duplicate rules into this skill — copies drift. Load from:

  • The umbrella note: concept-bible-platinum.
  • Domains / indexes:
  • 📤 Outreach & external leads (priority #1): _Bible-Outreach-MOC
  • 🏢 Operations: _Operations-Bible-MOC · Trello cards: _Bible-Trello-Index
  • 🛒 Purchases: _Pokupki-Rules
  • 🙋 Anton's personal layer: concept-bible-personal
  • Altitudes (note prefixes): insight-* (principle) → protocol-* (playbook) → reglament-* (atomic rule) → decision-* (precedent).
  • Self-maintenance: protocol-bible-self-maintenance. Secrets boundary: decision-bible-secrets-quarantine.

How to load the right slice

Pull the narrow relevant slice for the task — not all 10 years.

  • By domain: open the matching MOC above.
  • By meaning: python $IMPORTS_ROOT/brain_ask.py "" (semantic search over the curated layer).
  • By keyword: grep reglament-* / protocol-* under 03-Insights\Operations\ and 05-Resources\Protocols\.
  • Filter by audience: load agent + both; skip human-only (needs live judgment).

Precedence — resolving conflicting rules

  1. Newer beats older on the same topic (Anton's law) — by date_established; the loser becomes superseded.
  2. Anton's explicit rules are protected — to override an origin: anton / authored_by: human rule, the new one must also be Anton's or carry supersedes:. Team/agent don't override Anton by date alone.
  3. Specific beats general (carve-outs).
  4. Priority flag must > should > may.
  5. Letter-vs-spirit clash (reglament vs insight) → escalate to Anton to rewrite the reglament.

consult → act → write-back

  1. Consult the slice before acting.
  2. Act by the rules. Consequential/irreversible (money, outbound to external people, commitments, access) → Tier-2: ask Anton (operating-agreement). Outbound lead messages = draft→approve, never autonomous.
  3. Gap → escalate to Anton; his answer becomes a new reglament-* (verbatim, with audience). "Error/gap → write the rule immediately."

Secrets quarantine

Because the Bible is now a prompt, never load or emit secrets (passwords, accesses, financial figures, "grey" techniques). They live outside the loadable Bible. See decision-bible-secrets-quarantine.

Relation to other skills

telegram-assistant and telegram-lead-outreach are channel playbooks under this contract — same precedence, same write-back, same secrets boundary. When they act on Anton's behalf, this skill's rules apply.

How to write a rule (dual-reader)

Verbatim from Anton · imperative WHEN → DO · self-contained + example · frontmatter (type, altitude, audience, theme, origin, authored_by, date_established, status, confidence, plus supersedes / superseded_by on replacement). Full standard: vault note protocol-bible-as-prompt. Step-by-step playbook with examples (even for a weak LLM): vault note protocol-bible-rule-authoring.


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.

  • 📦 All 101 skills: https://github.com/tonydzi/second-brain-starter-kit
  • 👤 Author: Anton Dziatkovskii — Telegram @tonydzi · WhatsApp +1 341 222 9178 · X @TonyStef_
  • 🧪 Engineers: want to test-drive this setup? Message me — I hand out free starter seeds to engineers who test and report back. Custom skill requests welcome.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.