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 mycelium-hq/ai-brain-starter --skill meeting-todosgit clone --depth 1 https://github.com/mycelium-hq/ai-brain-starterWrote 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/mycelium-hq/ai-brain-starter/meeting-todos)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/meeting-todos"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/meeting-todos/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/mycelium-hq/ai-brain-starter/meeting-todos"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/meeting-todos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00095 | $0.01653 |
| Opus 5.5 | $0.00038 | $0.00661 |
| Sonnet 5.5 | $0.00019 | $0.00331 |
| Haiku 4.5 | $0.00010 | $0.00165 |
Grade A, and why
meeting-todos 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 1mo 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting → To-Do Extractor
After a meeting, pull action items from the transcript/notes and update your to-do file.
Trigger
/meeting-todos — optionally followed by a meeting title or date, e.g.:
/meeting-todos→ uses the most recent meeting note/meeting-todos 2026-04-09→ finds meeting from that date/meeting-todos Team Sync→ finds meeting matching that title
Step 0 — Locate (or create) the to-do file
Run this first, before searching for the meeting note. A fresh-install vault may not have a to-do file yet, and you don't want to do all the extraction work only to discover at Step 5 that there's no destination.
- Try the common paths first (fastest — one
GloborReadper location, stop on the first hit):🏠 Home/✅ Get to-do.md(canonical layout)Home/✅ Get to-do.md✅ Get to-do.md(vault root)Home/TODO.md/TODO.md/tasks.md
- If none of those exist, read the user's vault
CLAUDE.mdfor a vault-map / to-do location hint. If the hint resolves to an existing file, use it and proceed to Step 1. - If still nothing, ASK the user before creating anything:
I don't see a to-do file in your vault. Want me to create
🏠 Home/✅ Get to-do.mdwith a basic structure (frontmatter + Inbox section) so the meeting items have somewhere to land? You can move or rename it later. - On yes, create the file with this canonical structure (replace
YYYY-MM-DDwith today's date in both places):
Tell the user where you put it, then proceed to Step 1.--- type: todo created: YYYY-MM-DD updated: YYYY-MM-DD --- # To-do ## Inbox - On no, stop here. Don't extract action items from a meeting you can't file anywhere; that's silent-no-op territory. Tell the user
/meeting-todosneeds a destination file and ask them to create one (or point you at where their tasks live) before re-running.
Cache the resolved to-do path mentally for Step 5 — don't re-search the filesystem there.
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.
- 1mo ago First seen · 157 lines · 95 tokens per session scan A 84b51bf5373e
meeting-todos is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (49 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 1,653 once invoked, about $0.0004 per session on Opus 5.5. 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
nightly
Canonical seven-leg nightly close-parity protocol. Eleven independently evidenced checkpoints cover synthesis, reconciliation, context hygiene, sweeps, heat, digest, runtime health, cognitive state, ledger capture/review, and vault sync.
Promote
Take a slice of the current conversation and promote it to a durable vault artifact — concept note, project update, person profile, or doctrine entry. Pairs with /close. /close writes the daily note (transient outcome record); /promote elevates specific insights to permanent vault content the framework can refer back…
codex-adapter
Route ONE bounded, mechanical task to the Codex CLI as a non-Claude executor, under the same review-before-merge gate as any other agent-produced diff. Use when the user explicitly asks to hand a task to Codex, or names OpenAI Codex / a non-Claude executor for a mechanical change (rename a symbol across files, add a…
open
Boot the session, load context from the vault, and surface what matters.
Stuck
Walk the 6-rung escalation ladder before declaring stuck or asking the principal. Most "stuck" is actually "haven't tried the next approach." Stopping is the last resort, not the first response.
start
The day-one first-run flow and the everyday home screen. On first launch, greet, run setup, then carry the operator into a real first win. On return, give a short briefing and action menu.