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-checkgit 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-check)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/tg-check"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/tg-check/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-check"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/tg-check.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 | $0.01589 |
| Opus 5 | $0.00035 | $0.00794 |
| Sonnet 5 | $0.00014 | $0.00318 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
tg-check 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/tg-check — both Telegram rails on THIS machine
The operator's order (2026-06-27): "every computer checks whether BOTH of its Telegram rails work — MCP and telethon."
A local self-test: this computer checks its own two Telegram rails. Not to be confused with the
hub-only connector-health-daily (centralized). The root canon = the house rule
reglament-shina-telegram-bez-mcp-i-svoya-sessiya-na-mashinu.
Why two steps (this matters, don't shortcut it)
- The telethon rail is checked DETERMINISTICALLY and SAFELY (a shared lock
_refresh_work_acct_a.lock→ noAUTH_KEY_DUPLICATED). - MCP cannot honestly be checked by a script — it is a harness stdio server, reachable only by the LLM inside a session.
The script gives the best deterministic signal (is the process alive? a fresh fatal in the log?), while the REAL
MCP verdict comes from THIS skill — probing the tool inside the session. Memory
mcp-health-check: NEVER spin up a second Telethon client as a health check (AUTH_KEY_DUPLICATED).
Step 1 — the deterministic detector (0 tokens)
PYTHONIOENCODING=utf-8 python "$USERPROFILE/.claude/scripts/tg_channels_check.py"
Prints the per-machine matrix: MCP (by process + the tail of mcp_errors.log — a fresh AuthKeyDuplicated
= the RED root cause; TypeNotFound = an outdated telethon) and the telethon rail (GREEN/RED via
tg_bus_read.py --check). Exit 1 = something is RED. Flags: --json, --notify (pings the bus on RED).
Step 2 — the REAL in-session MCP test (this decides the MCP verdict)
- Are the Telegram MCP tools present in this session at all? If
mcp__telegram__*are NOT loaded (absent from the tool list / ToolSearch cannot find them) → MCP is RED: not loaded into the session. - If they are — call ONE cheap read tool:
mcp__telegram__list_accounts(orget_me, expecting the work account). Answered without an error → MCP is GREEN. An error (AuthKeyDuplicated / timeout) → RED + the reason from the error. - ⚠️ Exactly ONE cheap call. Don't call
get_history/search_dialogs(heavy → they can take the MCP down).
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.
- 3d ago First seen · 87 lines · 70 tokens per session scan A b8d8f5ceaf90
tg-check is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (6 stars, last pushed 3d ago), licensed MIT. It adds 70 tokens to every session and 1,589 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
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
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.
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…
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…