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/catch-upnpx skills add gleanwork/cursor-plugins --skill catch-upgit 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 | $0.00089 | $0.01378 |
| Opus 5 | $0.00044 | $0.00689 |
| Sonnet 5 | $0.00018 | $0.00276 |
| Haiku 4.5 | $0.00009 | $0.00138 |
Grade A, and why
catch-up 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 catch-up — 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Catch Up
You are helping someone who's been away catch up on what they missed. Follow a systematic approach to gather, prioritize, and present information.
Input
Determine the time period from the user's request. If it is not clear, ask: "How long were you away? For example: last week, since Monday, or the past two weeks."
Core Principles
- Prioritize ruthlessly: They're already behind, don't overwhelm them
- Action items first: Things assigned to them are highest priority
- Be skeptical: Not everything that happened matters to them
- Less is more: Better to miss something minor than overwhelm with noise
Phase 1: Establish Time Window
Goal: Understand how long they were away
Actions:
- Use the time period from the user's request directly in Glean queries — Glean understands natural language dates like "last week", "past 2 weeks", "since Monday", etc.
Phase 2: Gather Information
Goal: Collect relevant updates from all sources
Actions:
-
Start with Glean's AI synthesis for a quick overview:
chat "What important things happened [time period]? Focus on announcements, decisions, and changes that would affect someone returning from time off." -
Gather specific details — in parallel via subagents if your host supports them, otherwise sequentially:
Meetings and Action Items
- Find meetings from [time period]. Extract decisions and action items, especially any assigned to the user or waiting for their input.
- Use:
meeting_lookup "[time period]"
Direct Mentions
- Search for mentions of the user during [time period]. Find questions waiting for them or tasks assigned to them.
- Use:
search "[user name] [time period]"andchat "Were there any questions or tasks assigned to [user] during [time period]?"
-
Compile results
Phase 3: Vet Each Item (CRITICAL)
Goal: Filter aggressively — BE SKEPTICAL
For each item found, evaluate:
Direct Impact Test
- Does this directly involve them or just happen near them?
- ✅ INCLUDE: Assigned to them, @-mentioned, their projects affected
- ❌ OMIT: Happened on their team but doesn't involve them
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 · 187 lines · 89 tokens per session scan A e83527a918d9
catch-up is a skill published in the GitHub repository gleanwork/cursor-plugins (4 stars, last pushed 12d ago), licensed MIT. It adds 89 tokens to every session and 1,378 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 catch-up, 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…