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/gleanwork/cursor-plugins/meeting-prepnpx skills add gleanwork/cursor-plugins --skill meeting-prepgit clone --depth 1 https://github.com/gleanwork/cursor-pluginsWhat 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 | $0.00074 | $0.01252 |
| Opus 5 | $0.00037 | $0.00626 |
| Sonnet 5 | $0.00015 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
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 2d 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.
This is a copy
100% identical to meeting-prep — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Prep
You are helping someone prepare for an upcoming meeting. Gather context from past meetings, related documents, and attendee information.
Input
Determine the meeting, topic, or person from the user's request. If it is not clear, ask: "Which meeting would you like to prep for? You can give me the meeting name, a topic, or the name of the person you're meeting with."
Core Principles
- Actionable prep: Focus on what they need to know, not exhaustive history
- Scannable output: Busy people need quick context
- Be skeptical of relevance: Not everything from past meetings matters
- Quality over completeness: 5 good talking points beats 20 random ones
Phase 1: Identify the Meeting
Goal: Find the specific meeting
Actions:
- Use meeting_lookup to find the meeting:
meeting_lookup "[topic or person name] upcoming" - If multiple matches, ask the user to clarify
- Extract meeting details: title, time, attendees
Phase 2: Review Past Instances
Goal: Understand history and open items
Actions:
-
Use Glean chat for synthesized meeting history:
chat "What happened in previous [meeting name] meetings over the past 2 months? What decisions were made and what action items are still open?" -
Compile:
- What was decided recently?
- What action items are still open?
- What topics come up repeatedly?
Phase 3: Gather Context
Goal: Find relevant documents and attendee info
Actions:
-
Search for related documents:
search query="[meeting topic]" updated="past_month" -
For 1:1s or meetings with unfamiliar attendees, look up people:
employee_search "[attendee name]" -
If key documents are found, use read_document to get details
Phase 4: Vet Content (CRITICAL)
Goal: Filter to what's actually useful for prep — BE SKEPTICAL
For each piece of context, evaluate:
Relevance to THIS Meeting Test
- Will this actually come up in this meeting?
- ✅ INCLUDE: Directly relates to likely agenda items
- ⚠️ MAYBE: Tangentially related
- ❌ OMIT: Historical but not relevant to upcoming discussion
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.
- 2d ago First seen · 200 lines · 74 tokens per session scan A fbaf4545398f
meeting-prep is a skill published in the GitHub repository gleanwork/cursor-plugins (4 stars, last pushed 12d ago), licensed MIT. It adds 74 tokens to every session and 1,252 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to meeting-prep, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.