Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/michaeljauk/brain-starter/sync-brain-starter)<a href="https://agentmods.dev/skills/michaeljauk/brain-starter/sync-brain-starter"><img src="https://agentmods.dev/badge/skills/michaeljauk/brain-starter/sync-brain-starter.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 | $0.00047 | $0.01124 |
| Opus 5 | $0.00023 | $0.00562 |
| Sonnet 5 | $0.00009 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
sync-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 5d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Brain Starter
Syncs reusable parts from the private brain repo (~/brain) to the public template repo (~/tech/brain-starter). Copies skills, configs, and templates — then shows a diff for review before committing.
Trigger phrases
/sync-brain-starter- "sync brain starter"
- "push changes to the template"
- "update brain-starter"
Step-by-step workflow
1. Run the sync script
bash ~/brain/scripts/sync-brain-starter.sh
This copies:
- Vault skills (curated list):
wrap-session-up,ingest-article,defuddle,obsidian-cli,obsidian-markdown,obsidian-bases,json-canvas,gws-obsidian-prep,project-sync,research-spike,save-answer,lint-brain,qmd,find-skills,sync-brain-starter - Configs:
commitlint.config.js,.husky/commit-msg,docs/templates.md,docs/integrations.md
It does NOT copy:
CLAUDE.md,README.md,package.json,.claude/memory/MEMORY.md-- these are generalized differently in the template- Global/plugin skills -- brain-starter no longer bundles plugin skills (gstack, gws, todoist, m365, etc.). Users install these globally via their own install commands.
2. Review the diff
cd ~/tech/brain-starter && git diff
Run the leak gate. Do not eyeball the diff.
bash docs/scripts/leak-gate.sh --worktree
Reading a diff is not a check. Edit the TERMS list in that script first — it should name every
client, employer, colleague, product and account that must never reach the public copy, plus the
token shapes for secrets. Keep the script in the private repo; the list is itself sensitive.
A hit is a blocker. Replace it with a placeholder (acme, jane-doe, your-org.atlassian.net,
ACME-123, ~/), then run the gate again. Do not report the sync as clean until the command
prints nothing.
To judge whether the public repo was ever exposed, scan the history, not the tree.
git grep <rev> searches that revision's tree and says nothing about older commits:
bash docs/scripts/leak-gate.sh --history.
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.
- 5d ago First seen · 109 lines · 47 tokens per session scan A b52510acf072
sync-brain-starter is a skill published in the GitHub repository michaeljauk/brain-starter (5 stars, last pushed 9d ago), licensed MIT. It adds 47 tokens to every session and 1,124 once invoked, about $0.0002 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
pos-verify
Use this immediately after files are created, edited, moved, deleted, or materially rewritten inside PersonalOS. Verifies that new truth was routed to the correct owner, written in the correct file shape, and still follows POS conventions. Do NOT use for whole-vault deep audits; use system-health-check.
log
Use this when a PersonalOS work session, chat outcome, personal reflection, or provided source should be persisted into the modular Daily context and any already-owned canonical files. Do NOT use for single-call processing, single-source knowledge ingestion, Gmail/WhatsApp propagation, or Lexware booking.
task-manager
Use this when {{username}} or an agent wants to add, review, prioritize, complete, defer, park, or inspect todos, open loops, confirmed actions, waiting states, or attention triggers. Maintains atomic records under operations/actions/ and operations/attention-triggers/ as the only local action truth. Do NOT use for…
context-compression
Сжатие исторического контекста контуров и проектов: поддержка meetings/README.md как краткой памяти по прошлым встречам, решениям, разворотам, открытым вопросам, устаревшим договорённостям и якорным встречам. ОБЯЗАТЕЛЬНО используй этот скилл, когда пользователь просит: «сожми историю», «сделай скользящее окно»…
jtbd-to-interface
Генеративная трансформация JTBD в спецификацию интерфейса. Jobs порождают экраны, а не проверяют их. На входе: нормализованные JTBD (job statements, job maps, outcomes, персоны). На выходе: Screen Spec — какие экраны существуют, что на них, какой flow между ними, какие варианты по персонам. ОБЯЗАТЕЛЬНО используй этот…
landing-copywriter
Пишет Hero (H1 + subhead + proof + CTA) и ключевые блоки лендинга по 7-шаговому протоколу: Schwartz awareness → ядро позиционирования Trout/Ries с лакмус-тестом подстановкой конкурента → 10 кандидатов H1 → фильтр по 5 осям (brand-ownable, фальсифицируется, визуализируется, ритм, чистота текста) → 3 финалиста →…