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 cofounder-watchgit 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/cofounder-watch)<a href="https://agentmods.dev/skills/tonydzi/second-brain-starter-kit/cofounder-watch"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/cofounder-watch/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/cofounder-watch"><img src="https://agentmods.dev/badge/skills/tonydzi/second-brain-starter-kit/cofounder-watch.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 | $0.00109 | $0.00978 |
| Opus 5 | $0.00055 | $0.00489 |
| Sonnet 5 | $0.00022 | $0.00196 |
| Haiku 4.5 | $0.00011 | $0.00098 |
Grade A, and why
cofounder-watch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cofounder-watch — Phase 0 ambient cofounder (ping-only)
🧒 When reporting to a non-technical operator: finish with a child-simple "In plain words" recap in their language. Not inside the cofounder advice itself. 📖 Canon: [[decision-realtime-cofounder-2026-07-02]]. This is the EYES + filter of the real-time cofounder (Phase 0). It sends nothing — it only highlights.
What it does
A deterministic signal-dispatcher (0 tokens, stdlib only): reads the live funnel tg_followups.json → classifies salient events (the same rules as /pipeline) → dedups through cofounder_ledger.json (never pings twice) → writes a digest + an HTML dashboard. Silent when there are no new important events — that is the whole point: do not nag.
How to run
python "$IMPORTS_ROOT/cofounder/cofounder_watch.py" --stdout
- Flags:
--stdout(print the digest),--reset(clear the ledger → re-alert everything). - Outputs: digest
$IMPORTS_ROOT/cofounder/cofounder-digest.md; dashboard$OBSIDIAN_VAULT/_Dashboards/Cofounder-Watch.html(the operator works visually).
Salience (rules = /pipeline priority)
- 🔥 HIGH — they replied, Calendly NOT sent → "send the Calendly now".
- ⏰ MEDIUM — Calendly sent >24h ago, no booking → "booking nudge".
- 👀 LOW — pitch sent, no reply → "check inbound / follow up / drop".
- booked/confirmed → skipped (we do not re-pitch).
Boundaries (Phase 0)
- Ping-only — it NEVER messages leads. Actions are executed by the operator (or via
/pipelinedraft→approve). Human in the loop. - 0 tokens — the advice is templated from the rule. The LLM persona
/cofounderfor nuance is Phase 0.5 (later, HIGH events only). - Empty ≠ broken: "silent" is a valid result.
Next (Phase 0.5 / 1+, on the operator's greenlight)
- Delivery into a Telegram signal chat (once the MCP is alive) instead of a file + dashboard only.
- Scheduling on the HUB (always-on
HUB-1) 2-3x/day — this is background work, so it belongs on the hub, not the laptop, via/scheduleon the hub or the machine bus. Being lightweight (0 tokens), daytime runs are fine. - Phase 0.5: HIGH events → the LLM persona
/cofounder(top model) for nuanced advice. - Phase 1: + urgent VC email + calendar conflicts (same mailbox + ledger).
- To extend it, add a source to the SAME dispatcher; do NOT breed watchers ([[telegram-eventloop-listener]]: one live client, the AUTH_KEY pitfall).
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.
- 8d ago First seen · 56 lines · 109 tokens per session scan A d100f8e1adce
cofounder-watch is a skill published in the GitHub repository tonydzi/second-brain-starter-kit (5 stars, last pushed 9d ago), licensed MIT. It adds 109 tokens to every session and 978 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
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-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…
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.
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.
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
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…