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.
npx skills add tonydzi/second-brain-starter-kit --skill grok-syncgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWrote 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/tonydzi/second-brain-starter-kit/grok-sync)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/grok-sync"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/grok-sync/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.
<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/grok-sync"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/grok-sync.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00096 | $0.01538 |
| Opus 5.5 | $0.00038 | $0.00615 |
| Sonnet 5.5 | $0.00019 | $0.00308 |
| Haiku 4.5 | $0.00010 | $0.00154 |
Grade A, and why
grok-sync 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 11d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OBJECTIVE: Fold a Grok data export into the vault (one note per conversation + SQLite), idempotently. Reply to Anton in Russian; end with a 🧒 «Простыми словами» recap ([[eli5-always]]).
Why this shape (read before "fixing") — canon DR26-07-15-HUB-01
Grok has NO streaming/history API (the xAI API at api.x.ai is new-generations-only). The SANCTIONED rail is the on-demand bulk export → this skill parses that export; the "recurring" part is a weekly actor: trigger export → email link → download ZIP → parse (same family as [[takeout-pull]]). Incrementality is LOCAL (conversation_id + content_hash) because Grok re-exports the FULL archive each time.
⚠️ AUP (2026-06-26): xAI forbids automated access → the reverse cookie rail (/rest/app-chat/*) stays OFF by default; only turn it on by Anton's explicit decision. This skill only ever parses an export you were given — no network.
Step 0 — Get the export (human gate, then a weekly actor)
If no fresh Grok export is on disk:
- grok.com → Settings → Data Controls → Export Data (or
accounts.x.ai/data) → email with a download link → ZIP underttl/30d/export_data/<uuid>/containingprod-grok-backend.json(+prod-mc-asset-server/for media). - Interactive X/Grok login / 2FA = HARD-STOP → escalate to Anton (never enter credentials). Download of his OWN export = pre-authorized (drive his logged-in Chrome).
- The download link is time-limited — pull it inside the window (the [[takeout-pull]] actor pattern: detect the "ready" mail, download in time).
- ⚠️ X data archive ≠ grok.com history (separate stores, confirmed by [аккаунт] 2026-07-15) — do NOT use the X archive as the rail.
Step 1 — Import (idempotent, stdlib, 0 tokens)
Point the importer at the extracted prod-grok-backend.json:
python "$HOME/Obsidian/_imports/grok/grok_lib.py" import "<path-to-prod-grok-backend.json>"
It: normalizes wrappers (conversation + responses[], mixed ISO/BSON times, human→user) → upserts into grok_conversations.db (keyed by conversation_id; re-writes only when content_hash changed) → writes ONE note per conversation under 01-Conversations/Grok/conversations/ (thinking traces in <details>) → writes _freshness.json.
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.
- 11d ago Changed · -1 lines 85314e00f56c
- 16d ago Changed · +13 lines b5b1164a0324
- 25d ago First seen · 47 lines · 96 tokens per session scan A fe95b5c00541
grok-sync is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (9 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 1,538 once invoked, about $0.0004 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 2026-09-24.
Other skills, from other repositories
setup-vault-types
Use when configuring which document types a vault tracks: after installing ai-brain-starter, when a new kind of note appears (journals, books, meetings, clients, podcasts, travel, WhatsApp/Slack/iMessage exports), when extraction skips files because no extractor matches their type, or to add, list, or remove a custom…
ingest-health
Use when the user says /ingest-health, asks to import, sync, ingest, or load Apple Health / Apple Watch / HealthKit data, has a fresh export.zip from the iPhone Health app, a Simple Health Export CSV folder, or a Health Auto Export TCP live feed, or when health-mcp queries return empty because no data was ever…
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.
email-sorting
Customize and use a human-reviewed email sorting system for Gmail, Google Workspace, Outlook, Microsoft 365 or another connected mailbox. Use for first-time setup, folder or label recommendations from a read-only email sample, inbox triage, and applying approved sorting batches. Not for sending, replying to or…
ingest
A tool for adding a URL, file, text, or Inbox item to the LLM Wiki. It checks the material's purpose, preserves the original source, compiles a wiki page, updates indexes and logs, and reviews the result.
inbox
An inbox-management skill for scanning an LLM Wiki inbox, previewing pending files, choosing how to process them, and sending selected material through an import step.