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/commentsnpx skills add tonydzi/second-brain-starter-kit --skill commentsgit clone --depth 1 https://github.com/tonydzi/second-brain-starter-kitWhat 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 | $0.00079 | $0.01314 |
| Opus 5 | $0.00039 | $0.00657 |
| Sonnet 5 | $0.00016 | $0.00263 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
comments 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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/comments — comments under our content (show · reply · grow into a DM)
🧒 End the report to a non-technical owner with a short "In plain words" recap. (memory
eli5-always)
One pass: show the comments and reply surgically where a reply is actually expected. It collects and displays; it sends replies only on the owner's explicit "+". A thin layer (AK-47) over the engines in $IMPORTS_ROOT/content-factory\registry\.
🔴 BATTLE LESSON 2026-07-15 (memory
bulk-replies-cringe-one-offer-converts). The goal "zero unanswered" is CANCELLED: a batch of 16 replies to old comments was deleted by the owner in full ("my batch went out… I'm embarrassed myself"), comment auto-posting was turned off, and one of our accounts lost access to a third-party group. In the same night ONE public call-to-action post landed a partner within 30 hours. → Default = stay silent. Reply only if: it is addressed to us OR the thread is alive (younger than ~a week) OR a person is personally waiting for an answer. Older than that — skip, and that is NOT a debt. → Ceiling ≤3 replies per pass, never as a back-to-back series inside someone else's group: pace and volume read as a bot regardless of how good the text is. → Value is measured in people who moved, not in the unanswered counter.
Boundaries: this is about comments under OUR published posts (pubmetrics.db). The separate club corpus has its own skill (/sostav-comments). Facebook comments will be pulled in once the Graph token is live — for now the source is Telegram.
1. Fresh collection (0 tokens)
First refresh the database so you don't reply to stale material:
python tg_comments_collect.py(idempotent; exit 3 = the sending rail is busy → say "retry later", don't crash).
2. Show the state
python pub_metrics.py status— how many unanswered in total.python pub_comments_report.py— digest of the unanswered ones (spam bots fromspam_authors.txtare already flagged 🤖 and filtered out).python pub_metrics.py top-commenters --n 15— who comments most often.
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.
- 2d ago First seen · 66 lines · 79 tokens per session scan A 00427f377c2d
comments is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 1,314 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.