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/onboardingnpx skills add gleanwork/cursor-plugins --skill onboardinggit 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 | $0.00092 | $0.01692 |
| Opus 5 | $0.00046 | $0.00846 |
| Sonnet 5 | $0.00018 | $0.00338 |
| Haiku 4.5 | $0.00009 | $0.00169 |
Grade A, and why
onboarding 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 yesterday.
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 onboarding — 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Onboarding
You are helping someone new get up to speed on a team or project. Gather essential context about people, documents, and current priorities.
Input
Determine the team or project from the user's request. If it is not clear, ask: "Which team or project would you like to onboard onto? For example: payments team, search infrastructure, or a specific project name."
Core Principles
- Actionable over comprehensive: Focus on what to read and who to talk to
- Technical and social: Include both code context and people context
- Be skeptical: Not every doc found is essential reading
- Quality over quantity: 5 must-read docs beats 20 "might be useful" links
Phase 1: Get Overview
Goal: Quick understanding of the team/project
Actions:
- Use Glean chat for a synthesized overview:
chat "Give me an overview of the [team/project]. What do they own? What are their main responsibilities? What are they working on?" - Summarize the overview for context
Phase 2: Find Key People
Goal: Identify who to meet and learn from
Actions:
-
Find team members:
employee_search "[team/project]" -
Build a people map:
- Leadership: Who runs this team?
- Senior folks: Who are the experienced people?
- Recent hires: Who else is new?
Phase 3: Find Key Documents
Goal: Identify must-read docs and current priorities
Actions:
-
Search for foundational docs:
search "[team/project] onboarding OR getting started OR architecture" -
Search for recent activity:
search query="[team/project]" updated="past_month" -
Find recent team meetings for current priorities:
meeting_lookup "[team/project] past 2 weeks"
Phase 4: Vet All Content (CRITICAL)
Goal: Filter to truly essential items — BE SKEPTICAL
For each document, evaluate:
Essential Reading Test
- Does someone new NEED to read this?
- ✅ MUST-READ: Foundational understanding, will be referenced constantly
- 📚 HELPFUL: Good context but not required to start
- ❌ SKIP: Nice to have, can find later, or outdated
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.
- yesterday First seen · 253 lines · 92 tokens per session scan A b2fe44f497b1
onboarding is a skill published in the GitHub repository gleanwork/cursor-plugins (3 stars, last pushed 12d ago), licensed MIT. It adds 92 tokens to every session and 1,692 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to onboarding, 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…