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 agentmods add skills/tonydzi/second-brain-starter-kit/fb-watchnpx skills add tonydzi/second-brain-starter-kit --skill fb-watchgit 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/fb-watch)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/fb-watch"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/fb-watch.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 | $0.00076 | $0.02524 |
| Opus 5 | $0.00038 | $0.01262 |
| Sonnet 5 | $0.00015 | $0.00505 |
| Haiku 4.5 | $0.00008 | $0.00252 |
Grade A, and why
fb-watch 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 6d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fb-watch — finishing the teasers for the owner's Facebook posts
Why. The owner sometimes writes a post STRAIGHT onto his Facebook wall, bypassing the pipeline (voice → episode → tiers). Such a post ends up WITHOUT a teaser in the RU chat / X (EN) → reach is lost. This watchdog catches "there is an authored Facebook post with no teaser yet" and writes the teasers immediately. Draft-first until armed.
Tools (a thin orchestrator, AK-47)
- Reading the wall = the Claude-in-Chrome MCP (a live logged-in Facebook tab, locally on the hub). Reuses the pattern from
/fb-reply(in-pagejavascript_tool, since Facebook hides names behind the MCP boundary).- ⛔ Do NOT read the profile feed (consensus #0223a74a, 07-20): it is virtualized and renders ONE post — the neighbours stay eternal skeletons,
scrollHeightis constant, and real scrolling does not help. One run hid 2 content posts out of 5 that way. - ✅ The harvesting rail = the Content Library:
https://www.facebook.com/professional_dashboard/content/content_library/→ a table of posts, FULL text (truncation is CSS-only), exact date-time, metrics. Parsing:document.body.innerText→ lines, anchor on"Published", the text is the line before, the date the line after; accumulate across scrolls (dedupe by the first 60 characters). - ⚠️ The Content Library does NOT give permalinks (the row menu only has Edit/Delete). To get them: on the wall, do a real
computer hoverover the post timestamp → Facebook fillspfbidintohref(before hovering the href is empty; synthetic MouseEvents and React-fiber tricks do NOT work — Facebook uses a custom renderer key). - UPGRADE (owner approved 2026-06-30, waiting on credentials): as soon as
secrets\fb_graph.envexists (FB_USER_TOKEN,user_posts) andpython ~/.claude/scripts/fb_posts_poll.py checkis green → read the wall throughpython ~/.claude/scripts/fb_posts_poll.py posts --limit 10 --out posts.json(Graph API, more reliable than the browser, no ban risk) INSTEAD of Claude-in-Chrome. See [[decision-social-posting-stack]] §6.
- ⛔ Do NOT read the profile feed (consensus #0223a74a, 07-20): it is virtualized and renders ONE post — the neighbours stay eternal skeletons,
- Detector/ledger/cap =
python ~/.claude/scripts/fb_teaser_watch.py(0 tokens, dedup + daily cap + kill switch). State:$IMPORTS_ROOT/content-factory/fb_teaser_ledger.json+fb_watch_config.json. - Teasers are written by the top-tier model in-session (the owner's voice), palettes:
_STYLE.md/_CRAFT.md+style-reality-show.md. Drafts →_imports\content-factory\fb-teasers\<id>.md. - RU posting = Telegram MCP
send_message, the secondary work account (the creator), chat <YOUR_CHAT_ID> (the RU chat). EN/X = no poster yet → ALWAYS a draft (waiting on the social-tools DR).
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.
- 6d ago First seen · 70 lines · 76 tokens per session scan A 64db3a3cfe0f
fb-watch is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 6d ago), licensed MIT. It adds 76 tokens to every session and 2,524 once invoked, about $0.0004 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
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
wiki
Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.