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/codebase-contextnpx skills add gleanwork/cursor-plugins --skill codebase-contextgit 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 | $0.00042 | $0.01031 |
| Opus 5 | $0.00021 | $0.00515 |
| Sonnet 5 | $0.00008 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
codebase-context 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 codebase-context — 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Context
Gather comprehensive architectural context about an internal system by searching code and documentation across the organization.
Determine the system name from the user's request. If not specified, ask before proceeding.
Core Principles
- Breadth before depth: Find all relevant pieces before diving deep
- Docs + code: Both tell important parts of the story
- Be skeptical: Not every search result is relevant context
- Freshness matters: Stale docs can mislead
Process
Phase 1: Find the Code
Search for the system's codebase across all repositories:
code_search "[system] main OR core updated:past_month"
code_search "[system] service handler"
Look for:
- Main entry points and core modules
- API definitions (REST, gRPC, GraphQL)
- Key data structures and models
Phase 2: Find the Documentation
Search for architecture and design docs:
search "[system] architecture OR design doc"
search "[system] RFC OR proposal"
search "[system] runbook OR playbook"
Phase 3: Identify Key Contributors
Find who's actively working on this system:
code_search "[system] owner:* updated:past_month"
Cross-reference with employee_search for contact info.
Phase 4: Vet All Content
For each piece of content, evaluate:
| Test | ✅ Include | ⚠️ Note | ❌ Reject |
|---|---|---|---|
| Relevance | Core component, directly relevant | Mentions system but not central | Keyword coincidence |
| Currency | <6 months, matches code | 6-12 months | 12+ months with no activity |
| Authority | Approved RFC, design doc, official runbook | Team wiki, notes, drafts | Outdated proposals, abandoned work |
| Doc/Code consistency | Docs reflect current state | Note discrepancy, prefer code | Doc significantly wrong — warn user |
Repository Health:
- ✅ ACTIVE: Commits in past month
- ⚠️ SLOWING: Last commit 1-6 months ago
- ❌ STALE: No commits in 6+ months
Phase 5: Generate Vetted Context Report
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 · 149 lines · 42 tokens per session scan A 6dc991ee8b93
codebase-context is a skill published in the GitHub repository gleanwork/cursor-plugins (3 stars, last pushed 12d ago), licensed MIT. It adds 42 tokens to every session and 1,031 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 codebase-context, 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…