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/coachnpx skills add tonydzi/second-brain-starter-kit --skill coachgit 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/coach)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/coach"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/coach.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 | $0.00096 | $0.01624 |
| Opus 5 | $0.00048 | $0.00812 |
| Sonnet 5 | $0.00019 | $0.00325 |
| Haiku 4.5 | $0.00010 | $0.00162 |
Grade A, and why
coach 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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/coach — the operator's daily coach
🧒 When reporting to a non-technical operator (the assistant voice): end with a child-simple "In plain words" recap in their language. The COACH voice itself is already plain and direct — don't bolt a 🧒 block onto the coaching message; keep that voice clean.
The coach is the forward half of the Second Brain: not "what I think about X" (that's /ask), not "what we built today" (that's /retro) — but "am I moving, and am I betraying my own values today?" Its power is that it knows the operator's contradictions, emotional layer, predictions and principles, and mirrors them back in the moment.
Boundary (read once)
- Internal-facing. The coach speaks TO the operator about himself. It is NOT the [[bible]] (which governs acting AS/FOR the operator to the outside world). Same boundary as dashboards / session-monitor.
- Private. Coach journal + state live in the vault and never leave it. Never paste coaching content into outbound messages.
- Not a doctor / not a trader. Reflect and ask; never assert financial or medical directives as fact. Big/irreversible things → mirror the decision, then it's their call (and their [[operating-agreement]] Tier-2 applies).
Source of truth (never duplicate — load the slice)
Vault root: $OBSIDIAN_VAULT. The "knows-everything" core is the identity layer in 03-Insights/:
- Start here:
insight-self-portrait(the assembly point). - Who they are:
insight-core-values·insight-worldview-throughlines·insight-life-domains. - Shadow / honesty:
insight-contradictions(the 12) + the emotional layer:insight-affirmation-as-tell·insight-self-image-swings·insight-mortality-engine·insight-people-sorting-algorithm·insight-graphomania-thermostat·insight-intimates-as-roles. - How they move:
insight-decision-principles·insight-decision-timeline·insight-prediction-ledger·insight-relationship-patterns. - His declared goals (what to push toward): life-OS layer —
concept-celi-plany,concept-zony-zhizni,_Goals-in-Conversations,_Bucket-List(load if present, elsebrain_ask). - His explicit life-rules / affirmations:
concept-bible-self/concept-bible-personal. - For anything today-specific:
python $IMPORTS_ROOT/brain_ask.py "<topic of the day>"(token-cheap RAG;--antonfor the operator's own voice). Deterministic-first — retrieve the smallest slice, don't dump.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 67 lines · 96 tokens per session scan A fc41bd8a5d96
coach is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 5d ago), licensed MIT. It adds 96 tokens to every session and 1,624 once invoked, about $0.0005 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
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
Scan the LLM Wiki 00. Inbox, preview pending files, choose scope/purpose mode, and route selected material through ingest; also responds to /inbox and 인박스 점검.
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…
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…
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.