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/claude-plugins/searchnpx skills add gleanwork/claude-plugins --skill searchgit clone --depth 1 https://github.com/gleanwork/claude-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 | $0.00061 | $0.00735 |
| Opus 5 | $0.00030 | $0.00367 |
| Sonnet 5 | $0.00012 | $0.00147 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
search 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- search — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Glean Search
Perform a structured search across Glean enterprise knowledge and return vetted, quality-assessed results.
Core Principles
- Relevance over completeness: Show the best results, not all results
- Be skeptical: Not every keyword match is relevant
- Context matters: Include enough info to assess relevance
Search Process
1. Identify the Query
Determine the search topic from the user's request or current conversation context. If no query is apparent, ask the user what they want to search for before proceeding.
2. Execute Search
Use the Glean search tool with the user's query. Return the most relevant results.
3. Assess Results
For each result, evaluate:
Relevance:
- ✅ RELEVANT: Actually about the query topic
- ❌ SKIP: Keyword coincidence, different context
Currency:
- ✅ CURRENT: Recent update
- ⚠️ OLD: May be outdated
Only show results that pass the relevance check. If old, note it.
4. Present Vetted Results
For each included result:
- Title (as a clickable link if URL available)
- Source (app/datasource)
- Last updated (with freshness indicator: ✅ <6mo, ⚠️ 6-12mo, ❌ >12mo)
- Snippet (relevant excerpt)
- Relevance note (why this matches)
5. Note Quality
After results, include:
- How many results were found vs. shown
- Any concerns about result quality
- Suggestions if results seem limited
6. Offer Follow-up Actions
After showing results, offer these follow-up actions:
- Read a document in full
- Refine the search with filters (by date, owner, app/source, or different keywords)
- Search a related topic
Example Output
## Search Results: [query]
Found [X] results, showing top [Y] most relevant:
### 1. [Title] ✅
**Source**: Confluence | **Updated**: 2 weeks ago ✅
> [Relevant snippet...]
**Why relevant**: [Brief note on why this matches]
### 2. [Title] ⚠️
**Source**: Slack | **Updated**: 8 months ago ⚠️
> [Relevant snippet...]
**Why relevant**: [Note] | **Caveat**: May be outdated
---
**Quality note**: [X] results filtered out (keyword matches in different context)
**If these don't help**: Try [alternative search suggestion]
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 · 106 lines · 61 tokens per session scan A 39330b524321
search is a skill published in the GitHub repository gleanwork/claude-plugins (25 stars, last pushed 12d ago), licensed MIT. It adds 61 tokens to every session and 735 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.