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/glean_runnpx skills add gleanwork/cursor-plugins --skill glean_rungit 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 | $0.00014 | $0.01010 |
| Opus 5 | $0.00007 | $0.00505 |
| Sonnet 5 | $0.00003 | $0.00202 |
| Haiku 4.5 | $0.00001 | $0.00101 |
Grade A, and why
glean_run 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 glean_run — 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Glean Run
Discover and use Glean skills to help with enterprise app tasks (Jira, Slack, Google Workspace, Salesforce, etc.) or actions you don't already have a tool for. Where possible, aim to complete the user's request end-to-end rather than just listing available skills.
Authentication
Authentication is handled exclusively by the setup tool. If any other tool
returns a response containing [SETUP_REQUIRED], the user needs to
(re-)authenticate via setup.
When this happens:
- Call
setup(no arguments).- If no Server URL is configured,
setupreturns[SETUP_REQUIRED]with instructions. Relay them, ask the user for their work email, then callsetupagain withemailset to what they provided. - Once a Server URL is configured,
setupopens the Glean sign-in page in the browser and waits for sign-in.
- If no Server URL is configured,
- Once
setupreturns "Glean setup is complete", retry the original tool call.
Do not treat [SETUP_REQUIRED] as an error or try to work around it any
other way.
Step 0: Verify Setup
Call setup (with no arguments). If the connection isn't ready, setup
returns instructions — follow them and call setup again; it guides the whole
flow. Once it returns "Glean setup is complete", proceed to Step 1.
Step 1: Plan tool usage
A small set of popular tools is directly available, and no discovery is needed to use them. Discover is complementary and recommended if the direct tools cannot satisfy the user request end to end.
Calling find_skills_and_tools
If no arguments were provided and the task can't be inferred from conversation context, ask the user what they'd like to do before proceeding.
Call find_skills_and_tools with the task descriptions.
Break the request into small, task-atomic queries — keep only the core action,
dropping the surrounding context (recipients, timing, reasons, constraints) —
and pass each as a separate entry in queries.
find_skills_and_tools({
queries: [
"<atomic sub-task 1>",
"<atomic sub-task 2>"
]
})
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 · 125 lines · 14 tokens per session scan A fc6a3562f8e1
glean_run is a skill published in the GitHub repository gleanwork/cursor-plugins (3 stars, last pushed 12d ago), licensed MIT. It adds 14 tokens to every session and 1,010 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to glean_run, 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…