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 tg-postgit 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/tg-post)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/tg-post"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/tg-post/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/tg-post"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/tg-post.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 | $0.00070 | $0.01058 |
| Opus 5 | $0.00035 | $0.00529 |
| Sonnet 5 | $0.00014 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
tg-post scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tg-post — post to OUR Telegram channel (by registry, draft-first)
Why. On 2026-07-14 a TG post was blocked by a name collision: a stranger's channel vs ours, near-identical handles. Class-level fix: the channel is resolved ONLY by id from the registry, never by a name match.
0. Safety catch (mandatory)
python "$USERPROFILE/.claude/scripts/_shared/social_guard.py" check tg --text "<final text>"
BLOCKED (exit 3) → STOP and report to the operator (daily limit hit, or duplicate text). Do not work around it.
1. The channel — strictly from the registry
Truth = the vault note 00-System\Channels-Registry.md (verified live: id + admin status). In short (as of 2026-07-14):
- the RU channel
<YOUR_CHAT_ID>— RU teaser + longread ✅ - the EN channel
<YOUR_CHAT_ID>— EN teaser ✅ - the lab/hub channels — ⏳ no admin rights yet, do NOT post until rights are granted
- ⛔ the look-alike handle
<YOUR_CHAT_ID>— SOMEONE ELSE'S, never Runtime check:get_chatby id → the username in the reply matches the registry → good. Channel not in the registry → block, ask the operator (and add it to the registry once answered).
2. The account — depends on the machine and the channel
TG sessions are per-machine: first run list_accounts on YOUR machine. LAPTOP-1 = default (@work_acct_a); the hub = work_acct_b. Requirement: the account must be an admin of the channel (the registry records this). The owner's voice = the top model (a cheap grunt model never writes authored text).
3. Tier-2 gate (draft-first)
Show the operator: the final text + the channel (handle + id) + the account → wait for an explicit +. The only exception is a hardened routine with a standing mandate (like the fb-watch RU teaser).
4. Send + proof
send_message(chat_id = the id from the registry,parse_mode: "md"when using markup).get_message_linkby message_id → a live link is the proof of publication.python .../social_guard.py record tg --text "<text>".- Report in one line: the link + "tg today N/10".
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 · 64 lines · 70 tokens per session scan A 6e172ef63009
tg-post is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (6 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 1,058 once invoked, about $0.0003 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 2026-09-09.
Other skills, from other repositories
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.
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.
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…