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/find-expertnpx skills add gleanwork/cursor-plugins --skill find-expertgit 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 | $0.00152 | $0.01081 |
| Opus 5 | $0.00076 | $0.00541 |
| Sonnet 5 | $0.00030 | $0.00216 |
| Haiku 4.5 | $0.00015 | $0.00108 |
Grade A, and why
find-expert 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 2d ago.
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 find-expert — 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Find Expert
Find people who actually know about a topic — not just by org chart, but by real contributions and activity.
Clarify the topic
Work from the topic the user named. If it is ambiguous, ask a brief clarifying question before searching — for example, whether they need someone to answer questions, review code, or make a decision, and whether this is a specific internal system or a general technology. A single sentence of clarification is enough; don't interrogate.
Core Principles
- Activity over title: Someone actively contributing beats someone nominally responsible
- Multiple signals: Code + docs + discussions = true expertise
- Be skeptical: Just mentioning a topic doesn't make someone an expert
- Quality over quantity: 3 vetted experts beats 10 names
Phase 1: Gather Expertise Signals
Find people with multiple evidence of expertise:
-
Start with a synthesized answer from your knowledge tool:
chat "Who are the experts on [topic] at our company? Consider code contributions, documentation authorship, and meeting participation." -
Gather additional signals with direct searches:
employee_search "[topic]" code_search "[topic] contributors" search "[topic] RFC OR design doc" -
Cross-reference to find people appearing in multiple sources.
Phase 2: Vet Each Candidate
For each person found, evaluate:
| Test | ✅ Include | ⚠️ Caution | ❌ Reject |
|---|---|---|---|
| Evidence | Authored RFC, significant code contributions, documented expert | Single signal but significant | Single Slack mention, attended a meeting |
| Recency | Active in past 6 months | Active 6-12 months ago — note as historical | No activity in 12+ months |
| Role | Still on relevant team, still has context | Changed teams but retains knowledge | Left company, completely different role |
| Signals | 3+ independent signals | 2 independent signals | Single signal only |
Reject these:
- Single Slack mentions with no other evidence
- People who attended meetings but didn't contribute
- Names that appear in passing, not as experts
- Former employees
- People with outdated involvement
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.
- 2d ago First seen · 133 lines · 152 tokens per session scan A 90d36b9695b9
find-expert is a skill published in the GitHub repository gleanwork/cursor-plugins (4 stars, last pushed 12d ago), licensed MIT. It adds 152 tokens to every session and 1,081 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to find-expert, 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…