A one-time setup guide for a second-brain vault, which is a folder used to organise notes about your projects and code repositories.

Preparing a folder containing Git repositories for second-brain use, including creating project templates and starting the first sync.

It creates the needed project note files and registers the vault so later updates can be synchronised automatically.

setup — Skill by Imtylerrrrrr

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/imtylerrrrrr/second-brain/setup

Any agent

npx skills add Imtylerrrrrr/second-brain --skill setup

Clone the repo

git clone --depth 1 https://github.com/Imtylerrrrrr/second-brain

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 621 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 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.

Model	Per session	Once invoked
Fable 5	$0.00051	$0.00621
Opus 5	$0.00026	$0.00311
Sonnet 5	$0.00010	$0.00124
Haiku 4.5	$0.00005	$0.00062

Measured yesterday against content hash 357ff55a1ae0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup scanned grade B 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -qxF "<abs-vault-path>" ~/.claude/second-brain/vaults || echo "<abs-vault-path>" >> ~/.claude/second-brain/vaults

skills/setup/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

second-brain: setup

One-time onboarding of a vault (a folder containing the user's git repos). All operations are idempotent; never overwrite an existing user file.

Steps

Locate the vault root. Default candidate: the current working directory. Count git repos directly under it (ls -d */.git 2>/dev/null | wc -l). Present the candidate path + repo count and ask the user to confirm or supply a different absolute path. 0 repos → warn ("no git repos found here — sync will produce an empty board") but proceed if confirmed.
Scaffold Projects/ — copy each template only if the destination does not exist:
- ${CLAUDE_PLUGIN_ROOT}/templates/Projects/Dashboard.md → <vault>/Projects/Dashboard.md
- ${CLAUDE_PLUGIN_ROOT}/templates/Projects/_PROTOCOL.md → <vault>/Projects/_PROTOCOL.md
- ${CLAUDE_PLUGIN_ROOT}/templates/Projects/_TEMPLATE.md → <vault>/Projects/_TEMPLATE.md

Register the vault (idempotent):

mkdir -p ~/.claude/second-brain && touch ~/.claude/second-brain/vaults
grep -qxF "<abs-vault-path>" ~/.claude/second-brain/vaults || echo "<abs-vault-path>" >> ~/.claude/second-brain/vaults

First sync: bash "${CLAUDE_PLUGIN_ROOT}/scripts/sync.sh" — then read <vault>/Projects/_AUTO_status.md and report which repos were found and which stubs were created.
Merge the CLAUDE.md block. Read ${CLAUDE_PLUGIN_ROOT}/templates/CLAUDE-block.md. In <vault>/CLAUDE.md:
- file absent → create it containing exactly the block;
- file present without  → append the block at the end;
- markers present → replace everything between  and  with the current block (idempotent re-run).
Summarize: vault path, repos found, stubs created, note that the plugin's Stop hook now refreshes git facts automatically (best-effort), and next steps — /second-brain:start-session to begin; /second-brain:analyze <repo> to onboard notes properly.

Read the full file on GitHub · 37 lines

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.

yesterday First seen · 37 lines · 51 tokens per session scan B 357ff55a1ae0

Subscribe to this mod's changes

setup is a skill published in the GitHub repository Imtylerrrrrr/second-brain (1 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 621 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Git and workflow Memory and context Productivity anti-hallucination claude-code claude-code-plugin project-memory session-management

rubber-duck

Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…

kirodotdev/KiroCrew · 161 tokens

testing-api-authentication-weaknesses

Tests API authentication mechanisms for weaknesses including broken token validation, missing authentication on endpoints, weak password policies, credential stuffing susceptibility, token leakage in URLs or logs, and session management flaws. The tester evaluates JWT implementation, API key handling, OAuth flows, and…

xalgorix/xalgorix · 102 tokens

setup

Getting it into your agent

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

second-brain: setup

Steps

What this file has done since we first saw it

Other skills, from other repositories

rubber-duck

testing-api-authentication-weaknesses

Effective Memory

exam-study-guide

exam-ingest

oly-apps