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/using-gleannpx skills add gleanwork/cursor-plugins --skill using-gleangit 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 | $0.00171 | $0.01148 |
| Opus 5 | $0.00086 | $0.00574 |
| Sonnet 5 | $0.00034 | $0.00230 |
| Haiku 4.5 | $0.00017 | $0.00115 |
Grade A, and why
using-glean 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 using-glean — 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Glean
The Glean MCP server exposes a family of tools that let the assistant query the user's company knowledge: documents, people, meetings, email, internal code, the user's activity feed, structured memory, and the knowledge graph. This skill is the entry point. It maps a user's question to the right tool, names the rules that apply across all of them, and links to per-tool reference files that carry the deep syntax.
Where these tools live
The tools listed below come from the user's Glean MCP server connection. Refer to them by their bare names (search, employee_search, meeting_lookup, …) — the assistant resolves them against the active tool inventory.
In the raw MCP tool list, Glean tools appear as mcp__glean_[server-name]__[tool] where [server-name] is the user's configured server identifier (e.g., default, production, acme). The tool suffix after the final __ is always consistent across deployments. Use whatever Glean server is visible in your tool inventory.
If no Glean tools are visible, ask the user to set up Glean by prompting the
harness (for example, Set up Glean for me).
Intent → tool decision tree
| The user is asking about... | Reach for | Reference |
|---|---|---|
| Documents, wikis, policies, RFCs, specs | search |
search.md |
| A complex question that needs synthesis across sources | chat |
chat.md |
| Internal source code, files, commits across repos | code_search |
code-search.md |
| People, teams, org structure, reporting lines | employee_search |
employee-search.md |
| Meetings, transcripts, decisions, action items | meeting_lookup |
meeting-lookup.md |
| Gmail messages, threads, attachments | gmail_search |
gmail-search.md |
| Outlook messages, threads, attachments | outlook_search |
outlook-search.md |
| Reading a specific URL / document | read_document |
read-document.md |
| The user's own recent activity (standup, weekly summary) | user_activity |
user-activity.md |
| The user's stored memories / personalization | memory (+ memory_schema) |
memory.md |
| Structured entity / relationship queries | knowledge_graph_query (+ knowledge_graph_schema) |
knowledge-graph.md |
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/agents-as-tools.md 3.3 KB
- reference/chat.md 2.4 KB
- reference/code-search.md 2.8 KB
- reference/employee-search.md 3.7 KB
- reference/gmail-search.md 2.2 KB
- reference/knowledge-graph.md 3.8 KB
- reference/meeting-lookup.md 4.2 KB
- reference/memory.md 7.1 KB
- reference/outlook-search.md 2.3 KB
- reference/read-document.md 2.5 KB
- reference/search.md 5.3 KB
- reference/synthesis.md 4.8 KB
- reference/user-activity.md 2.4 KB
- reference/vetting.md 5.0 KB
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 · 55 lines · 171 tokens per session scan A 52fc10fd21d6
using-glean is a skill published in the GitHub repository gleanwork/cursor-plugins (3 stars, last pushed 12d ago), licensed MIT. It adds 171 tokens to every session and 1,148 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to using-glean, 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…