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 taskgit 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/task)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/task"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/task/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/task"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/task.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 | $0.00071 | $0.01152 |
| Opus 5 | $0.00036 | $0.00576 |
| Sonnet 5 | $0.00014 | $0.00230 |
| Haiku 4.5 | $0.00007 | $0.00115 |
Grade A, and why
task 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.
/task — delegating tasks to people, with a seed for THEIR Claude
The operator says "N understands this one better" → the task goes to them: a message in the delegation chat (short, human) + a seed file in the vault (full, for their Claude). They say a code phrase to their Claude, which unpacks the seed and starts immediately.
Constants
- Engine:
python ~/.claude/scripts/_shared/delegate.py(envDELEGATE_VAULTfor tests) - Seeds:
$OBSIDIAN_VAULT/10-Tasks\_seeds\<ID>.md(Syncthing carries them to every machine; the Mac path differs) - The delegation TG chat: id in memory [[delegation-chat-04-tasks]]; post from THIS machine's own account
- People:
nat·rusl·ant. IDs = NAT-1 / RUSL-2 / ANT-3, case-insensitive
A. DELEGATE (usually on the hub, on the operator's word)
- Write the SEED (self-contained, per the decompose canon: Outcome · Context + paths · Scope · Deliverable · DoD · non-goals · how to report back). Normal voice, no secrets ([[credential-store]]).
delegate.py new --to nat --title "<short>" --seed-file <f>→ prints the ID + a ready TG text.- Send that TG text to the delegation chat (Telegram MCP). The format is already in the engine output: "📌 @teammate_n · · from the operator / Code phrase: 'task NAT-1'". ⭐ The @mention is MANDATORY (2026-07-14): without a @username the person gets no notification and the message drowns. The same applies to every re-ping.
- Connect: you handed it over, so you own it until the result. No ACK within ~a day → re-ping in the delegation chat; continued silence → the hanging-tasks board + escalate to the operator.
B. UNPACK (the assignee's machine, on the code phrase)
- You hear "task NAT-1" / "my tasks":
delegate.py list --for nat/delegate.py get NAT-1. - The seed is not on disk yet (Syncthing lag) → say honestly "the file is still in transit", do not invent the task.
delegate.py ack NAT-1 --by "<machine>-<person>"+ an ACK in the chat: "✅ took NAT-1, starting".- Work from the seed like any other assignment (Tier-2 and the Bible still apply).
- Done:
delegate.py done NAT-1 --note "<outcome>"+ a one-line report in the chat + the artifacts per the DoD.
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 · 71 tokens per session scan A 2175b75a82a5
task is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (6 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,152 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 2026-09-09.
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.