bootstrap

An interactive first-run setup guide for a fresh copy of a personal knowledge workspace. It configures identity, the assistant's name, visual style, folder structure, and other settings.

In plain words
What is it for?
Use it once after creating a fresh fork to set up identity, name the assistant, choose a design system, create the PARA folders, configure the workspace, and optionally import existing material.
Why use it?
It turns an unconfigured workspace into a personalized one through a guided process, while showing proposed changes before writing them.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/the-sid-dani/second-brain-os/bootstrap
Any agent
npx skills add the-sid-dani/second-brain-os --skill bootstrap
Clone the repo
git clone --depth 1 https://github.com/the-sid-dani/second-brain-os

Made for: Claude Code, Codex.

Per session 250 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,089 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00250 $0.05089
Opus 5 $0.00125 $0.02544
Sonnet 5 $0.00050 $0.01018
Haiku 4.5 $0.00025 $0.00509

Measured 2d ago against content hash 4ee33be71cfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

bootstrap scanned grade C with 1 finding 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **PASS** → delete the throwaway, **guarded** (never an unguarded `rm -rf`): `P="<smoke-test-path>"; [[ -n "$P" && "$P" == *"/1-Projects/bootstrap-smoke-test-"* && -d "$P" ]] && rm -rf "$P"`. If it doesn't match, leave
.claude/skills/bootstrap/SKILL.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bootstrap

First-run setup. Walks a freshly-cloned fork through identity, naming your assistant (you always name your own — no default), a design system, the PARA workspace, configuration, and a quick smoke test — then offers two optional extras (writing voice from your sent messages; bringing in your existing work). A short, plain-language walkthrough — about 8-10 minutes for the core.

Why this is the most important skill: every fork user runs it exactly once, and the whole harness is built on what it writes. A broken /bootstrap ships a broken second brain to every fork.

Design principle — warm, brief, in control. This is for knowledge workers, not engineers. Open each step with one or two plain sentences on why it matters — not a script, not a wall of text, no jargon. Every write gets a preview + an AskUserQuestion gate before it happens; nothing is installed; nothing is committed. The feel is a sharp colleague walking you through it, never an "automated wizard." When in doubt, fewer words.

Tiger invariants (LOAD-BEARING — DO NOT VIOLATE)

The four tiger invariants are referenced by ID throughout this file. Canonical statements live here only.

T1 — NEVER overwrite user-edited persona files without explicit confirmation

If a root persona file (SOUL.md, USER.md, IDENTITY.md, CLAUDE.md, README.md, TOOLS.md) has been edited beyond what the persona template would produce, the apply step MUST detect this via git diff --quiet HEAD -- <file> and ask before overwriting. Default behavior: skip. Only overwrite when the user explicitly confirms.

T2 — NEVER re-run on an already-configured fork without explicit user action

Step 1 detects re-run via grep -E "^- \setup_completed` = " CLAUDE.md. If found, refuse and print: *"This fork is already configured (setup_completed: <date>). To re-run /bootstrap, delete the setup_completed` line in CLAUDE.md and invoke /bootstrap again. For partial edits, update the root Configuration section and the relevant persona file directly with the user's approval."* Do NOT proceed past Step 1. (The two optional go-further steps are separately re-invokable — see Step 6 — and do not trip T2.)

Read the full file on GitHub · 286 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 2d ago First seen · 286 lines · 250 tokens per session scan C 4ee33be71cfa

Subscribe to this mod's changes

bootstrap is a skill published in the GitHub repository the-sid-dani/second-brain-os (2 stars, last pushed 26d ago), licensed MIT. It adds 250 tokens to every session and 5,089 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

dr-fanout

One command to fan a Deep Research prompt out to several external LLMs at once (ChatGPT / Gemini / Grok / others) through the operator's logged-in browser, then collect the reports, archive the originals, and synthesize a consensus. Trigger on "/dr-fanout", "fan out the DR", "distribute the research prompt". Automates…

tonydzi/second-brain-starter-kit · 98 tokens

fb-reply

Read who commented on the owner's recent Facebook posts and post PERSONALIZED replies through their real logged-in Chrome (live-tab, low-ban-risk), draft-first and rate-limit-guarded. Trigger on "/fb-reply", "reply to my facebook comments". Replying on your OWN posts is expected behavior; the guard enforces a daily…

tonydzi/second-brain-starter-kit · 78 tokens

journey

Resurrect and continue a build-in-public BOOK — the serialized story of a founder + AI- cofounder journey. One command: pick up state (which days are written in which languages, what's uncommitted, where the gaps are), then continue writing via the established pipeline. Trigger on "/journey", "the book", "continue the…

tonydzi/second-brain-starter-kit · 76 tokens

3

Launch autonomous multi-machine consensus between Claude peers (hub + laptops + teammate machines): the peers negotiate a decision among themselves over a shared coordination channel and execute it, without using the human as a courier. Trigger on "/03" or phrases like "work it out among yourselves" / "find…

tonydzi/second-brain-starter-kit · 97 tokens

alfa-search-recall-deepresearch

Mandatory decision protocol ("Alpha Protocol") for any new STRATEGIC work — never jump to implementation on local recall alone. Run RECALL over the knowledge vault → GAP analysis → emit a DEEP RESEARCH PROMPT to run in external deep-research tools → SYNTHESIS + Decision Memo when results come back. Trigger on…

tonydzi/second-brain-starter-kit · 129 tokens

follower-onboard

Onboard a NEW family/team machine as a FOLLOWER-CONSUMER joining the multi-machine Claude+vault network. A follower READS the shared vault + canon + skills + memory as RECEIVE- ONLY data, runs nothing heavy locally (no RAG/reindex/GPU), and the hub never pushes executable hooks to it. Trigger on "/follower-onboard "…

tonydzi/second-brain-starter-kit · 99 tokens