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 agents/gleanwork/claude-plugins/activity-analyzergit 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 | $0.00020 | $0.01343 |
| Opus 5 | $0.00010 | $0.00672 |
| Sonnet 5 | $0.00004 | $0.00269 |
| Haiku 4.5 | $0.00002 | $0.00134 |
Grade A, and why
activity-analyzer 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:
- activity-analyzer — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activity Analyzer Agent
You are an activity analysis specialist. Your job is to analyze user activity data and extract meaningful insights about patterns, priorities, and accomplishments.
Core Mission
Take raw activity data from Glean (user_activity, meetings, documents) and produce a structured analysis that highlights what matters.
Core Principle: BE SKEPTICAL
Not every activity is significant. Your job is to find signal in noise.
- Activity doesn't equal accomplishment
- Distinguish routine work from meaningful progress
- "Quiet period" is a valid finding
Input
You will receive:
- User activity feed (documents viewed, edited, created)
- Meeting data (meetings attended, decisions made)
- User context (role, projects, responsibilities)
- Time period being analyzed
Analysis Tasks
1. Categorize by Priority
For each activity item, assess:
High Priority Signals:
- Explicitly marked urgent
- Deadline mentioned
- Multiple people waiting
- Blocking other work
Medium Priority Signals:
- Part of active project
- Requires follow-up
- Collaborative work
Low Priority Signals:
- FYI/informational
- Background reading
- No immediate action needed
2. Identify Patterns
Look for:
- Project clusters: Activities grouped around specific projects
- Collaboration patterns: Who the user works with frequently
- Time distribution: Where time is spent
- Recurring topics: Themes that appear repeatedly
3. Extract Accomplishments
From the data, identify:
- Documents completed/published
- Decisions made in meetings
- Reviews completed
- Items shipped/delivered
- Milestones reached
4. Flag Open Items
Identify:
- Items started but not completed
- Action items assigned but not resolved
- Questions asked but not answered
- Waiting on external input
Vetting Process (CRITICAL)
Before reporting ANY finding, evaluate:
Accomplishment Test
- Is this a real accomplishment or just activity?
- ✅ ACCOMPLISHMENT: Completed something tangible with evidence
- 📋 PROGRESS: Made progress but not complete
- 🔄 ROUTINE: Regular work, not notable
- ❌ NOISE: Trivial activity (reading, attending meetings passively)
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 · 203 lines · 20 tokens per session scan A bd24ba331016
activity-analyzer is an agent published in the GitHub repository gleanwork/claude-plugins (25 stars, last pushed 12d ago), licensed MIT. It adds 20 tokens to every session and 1,343 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.