What is update-brain-starter?

A controlled updater for the brain-starter vault template. It shows the release notes, compares template versions, and merges template-owned files while leaving the user's notes and content alone.

Use it to review and apply a newer brain-starter release, inspect conflicts, and update template files after agreeing to the proposed changes.

It provides a way to update shared templates without overwriting personal project notes, and requires approval before applying changes.

update-brain-starter — Skill for Claude Code by michaeljauk

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/michaeljauk/brain-starter

agentmods

npx agentmods add skills/michaeljauk/brain-starter/update-brain-starter

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/michaeljauk/brain-starter/update-brain-starter/github.svg)](https://agentmods.dev/skills/michaeljauk/brain-starter/update-brain-starter)

Your own site

<a href="https://agentmods.dev/skills/michaeljauk/brain-starter/update-brain-starter"><img src="https://agentmods.dev/badge/skills/michaeljauk/brain-starter/update-brain-starter/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/michaeljauk/brain-starter/update-brain-starter"><img src="https://agentmods.dev/badge/skills/michaeljauk/brain-starter/update-brain-starter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,678 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00086	$0.02678
Opus 5.5	$0.00034	$0.01071
Sonnet 5.5	$0.00017	$0.00536
Haiku 4.5	$0.00009	$0.00268

Measured yesterday against content hash 9080b3007084, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

update-brain-starter 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 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.

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.

.claude/skills/update-brain-starter/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update brain-starter

Brings the template-owned parts of this vault to a newer brain-starter release. The user's own content never changes: projects/, knowledge/, research/, decisions/, meetings/, tasks/, .claude/memory/, log.md, hot.md, and every file that the release does not list as owned.

Works for vaults made with "Use this template" and for clones. It does not use git history: it downloads the installed release and the target release from GitHub and merges three ways.

Trigger phrases

/update-brain-starter
/update-brain-starter 3.9.0 - a specific version instead of the latest
"update brain-starter", "update the template", "is there a new brain-starter version?"

Contract

The user decides. Show the changelog and the plan before anything changes. No apply without a yes to that plan in this conversation.
Never delete a file and never remove a hook on your own. The helper only proposes them. The one exception is a rename the user agreed to in the plan: apply moves the file and removes the old path. Do each one only after the user agrees to that item.
Every conflict gets an explanation. For each conflict: what the user changed, what the template changed, and a proposed resolution. The user picks.
Never commit without asking. One commit on the update branch, after the user's go.

Files

Path	Role
`.brain-starter.json`	Installed version, update check settings, the release's list of owned files
`docs/scripts/brain-starter-update.mjs`	Downloads both releases, classifies and merges files
`docs/scripts/brain-starter-check.sh`	SessionStart hook that prints the "new version" line

Step 1 - Plan

node docs/scripts/brain-starter-update.mjs plan            # or: plan --to 3.9.0

The output is JSON. If status is up-to-date, say so and stop.

Check the base before you trust the plan. localMatchesBase (for example 41/44) counts the owned files that are byte-identical to the installed release. A vault that matches its base mostly is normal. If fewer than half match, the installed version is probably wrong (an old vault from before .brain-starter.json existed reads it from .release-please-manifest.json). Ask the user which version they started from and rerun with --from X.Y.Z. Also tell the user where from came from (fromSource).

Read the full file on GitHub · 201 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 · 201 lines · 86 tokens per session scan A 9080b3007084

Subscribe to this mod's changes

update-brain-starter is a skill published in the GitHub repository michaeljauk/brain-starter (5 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 2,678 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-05.

Claude Code Git and workflow Releases ai-tools knowledge-management markdown obsidian obsidian-plugin

update-brain-starter next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
update-brain-startermichaeljauk/brain-starter	Skill	5	yesterday	MIT	A	86	Claude Code
release-rollbackdzhokhov/markdown-agent-vault-ru	Skill	2	2mo ago	MIT	A	101	Codex
git-wrapupcyanheads/obsidian-mcp-server	Skill	702	6d ago	Apache-2.0	A	109	Claude Code
release-and-publishcyanheads/obsidian-mcp-server	Skill	702	6d ago	Apache-2.0	A	155	Claude Code
release-pr-reviewcyanheads/obsidian-mcp-server	Skill	702	6d ago	Apache-2.0	A	136	Claude Code
release-slicetonydzi/second-brain-starter-kit	Skill	14	2d ago	MIT	A	76	Claude Code
hyalo-changelogractive/hyalo	Skill	27	today	MIT	A	24	Codex