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 mshadmanrahman/pm-pilot --skill meeting-prepgit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote 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/mshadmanrahman/pm-pilot/meeting-prep)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/meeting-prep"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/meeting-prep/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/mshadmanrahman/pm-pilot/meeting-prep"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/meeting-prep.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 | $0.00059 | $0.01244 |
| Opus 5.5 | $0.00024 | $0.00498 |
| Sonnet 5.5 | $0.00012 | $0.00249 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
meeting-prep 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Prep
Gathers cross-channel context before any meeting so you walk in fully prepared. Works for person-based prep (1:1s) and topic-based prep (product syncs, reviews).
When to Activate
- User says "meeting prep", "prep for my meeting with X", "prep for 1:1"
- User provides a person name or meeting topic to prepare for
- User says "what should I discuss with X?"
Input
The user provides ONE of:
- Person name: e.g., "Sarah Chen", "Marco", "the CTO"
- Topic/meeting name: e.g., "Q3 planning", "API migration review"
- Calendar event: a specific meeting from today's calendar
If no input, check Google Calendar MCP for the next upcoming meeting and prep for that.
Execution
Context Check
Before gathering, read context/company.md and context/personas.md if they exist. Use for framing output. After completing the briefing, offer to update context files with any new knowledge about people, projects, or company priorities discovered during research.
Step 0: Resolve Target
- Person name given: use as search target across all sources.
- Topic given: use as search query.
- No input: fetch next meeting from Google Calendar, extract attendees and title.
Step 0.5: Org-Survival + People File Check (Person-Based Only)
Before gathering from external sources, read two local files:
-
memory/org-survival.md— Check if person has an entry. Extract: what they want, risks they carry, recommended approach. Surface as Political Context block (2–3 lines max). Skip silently if not found. -
memory/people/{name}.md— Check for accumulated meeting history with this person. Extract: prior commitments they made (were they fulfilled?), communication style, known preferences. Fold into Their Current Focus and Suggested Talking Points.
This is the highest-signal step — it's the context no live API can replicate.
Step 1: Parallel Data Gathering (Fan-Out)
Launch parallel searches across all connected MCP sources.
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 · 131 lines · 59 tokens per session scan A 5e1a01ac47d7
meeting-prep is a skill published in the GitHub repository mshadmanrahman/pm-pilot (22 stars, last pushed 23d ago), licensed MIT. It adds 59 tokens to every session and 1,244 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
agent-teams
Multi-agent team orchestration with native Agent Teams. Trigger when the user wants to launch a team of agents, coordinate parallel work with inter-agent communication, or use swarm mode.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
keybindings-help
Use when the user wants to customize keyboard shortcuts, rebind keys, add chord bindings, or modify /.claude/keybindings.json. Examples: "rebind ctrl+s", "add a chord shortcut", "change the submit key", "customize keybindings".
outlook_calendar
View, create, update, and delete events in the user's Outlook Calendar.
granola
Search and read Granola meeting notes and transcripts through Granola's OAuth-backed MCP server.
getting-started
Interactive post-onboarding tour that adapts to whatever data exists (calendar, Granola, or none). Use right after onboarding, or when the user says 'show me around', 'how do I start'. Also use proactively when the vault is < 7 days old. Not for the initial setup itself; use setup.