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/plan-prepnpx skills add gleanwork/cursor-plugins --skill plan-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 | $0.00031 | $0.01231 |
| Opus 5 | $0.00015 | $0.00616 |
| Sonnet 5 | $0.00006 | $0.00246 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
plan-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 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 plan-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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning Preparation via Glean
Research enterprise context before entering plan mode by gathering design docs, similar implementations, stakeholders, and related systems.
When This Applies
Use plan prep when users:
- Want to research before entering plan mode
- Are planning architectural or strategic changes
- Need to understand related systems before designing
- Want to identify stakeholders and code owners early
- Ask: "plan with glean", "prep for plan", "research before planning"
Why This Matters
Better planning comes from enterprise context:
- Design Decisions: Understand what was tried before, why it worked or didn't
- Similar Implementations: Find proven patterns and learn from past approaches
- Stakeholders: Identify who needs to be involved or has relevant knowledge
- Related Systems: Understand dependencies and integration points
Local tools only see your current repo. This workflow searches your entire organization for existing decisions, patterns, and knowledge.
BE SKEPTICAL
Filter aggressively for relevant, current information.
| Test | ✅ Include | ⚠️ Note | ❌ Exclude |
|---|---|---|---|
| Freshness | <6 months | 6-12 months | 12+ months |
| Relevance | Directly applies | Similar context | Keyword match only |
| Authority | Approved RFCs, official docs | Team wiki, proposals | Rejected/abandoned work |
| Quality | Well-reasoned, proven | Has tradeoffs | Experimental, hacky |
Quality over quantity: 3-4 high-quality findings beat 10 weak ones.
Tool Selection
| Research Need | Glean Tool |
|---|---|
| Find design docs, RFCs, architecture | search |
| Find similar code implementations | code_search |
| Find code owners and stakeholders | code_search + employee_search |
| Find related/dependent systems | code_search |
| Read full document content | read_document |
Workflow
Phase 1: Search for Design & Architecture
Find design documents, RFCs, and architectural decisions related to the task:
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 · 180 lines · 31 tokens per session scan A 581022173b02
plan-prep is a skill published in the GitHub repository gleanwork/cursor-plugins (3 stars, last pushed 12d ago), licensed MIT. It adds 31 tokens to every session and 1,231 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to plan-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.
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…