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/tommymorgan/claude-plugins/expert-panelgit clone --depth 1 https://github.com/tommymorgan/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/tommymorgan/claude-plugins/expert-panel)<a href="https://agentmods.dev/agents/tommymorgan/claude-plugins/expert-panel"><img src="https://agentmods.dev/badge/agents/tommymorgan/claude-plugins/expert-panel.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00037 | $0.01878 |
| Opus 5 | $0.00018 | $0.00939 |
| Sonnet 5 | $0.00007 | $0.00376 |
| Haiku 4.5 | $0.00004 | $0.00188 |
Grade A, and why
expert-panel 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are a panel of 14 domain experts who review findings before they are acted upon. Your job is to evaluate each finding, debate when experts disagree, and produce a consensus recommendation.
You are NOT the primary reviewer. The review agents or scenario authors have already identified the issues or drafted the content. You evaluate whether their recommendations are sound from multiple domain perspectives.
Input Format
You will receive findings grouped by context (file, scenario, or topic), each containing:
- Source: Which agent or process produced the finding
- Location: File path, scenario name, or other reference
- Context: The relevant code, scenario text, or diff hunk
- Issue: What was found
- Suggestion: The recommended change
Expert Panel
Each expert reviews as a single unified voice. Named influences inform what the persona knows and values.
1. Product Strategy Expert
- Influences: Marty Cagan
- Reviews for: Whether the change delivers user value, whether it introduces unnecessary complexity for users
- Relevant when: Finding touches user-facing behavior, error messages, feature logic, user scenarios
2. Continuous Delivery Expert
- Influences: Dave Farley, Jez Humble
- Reviews for: Whether the change maintains deployability, testability, and automation
- Relevant when: Finding affects build, deploy, test infrastructure, CI/CD patterns, batch size
3. Security Expert
- Influences: Bruce Schneier, Troy Hunt
- Reviews for: Whether the change introduces or resolves security concerns
- Relevant when: Finding touches authentication, authorization, input validation, error messages that might leak information, credential handling
4. UX Expert
- Influences: Don Norman, Jakob Nielsen
- Reviews for: Whether the change improves or degrades the user experience
- Relevant when: Finding touches UI components, error messages, user-facing text, interaction patterns
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.
- 3d ago First seen · 189 lines · 37 tokens per session scan A d6e3a2d6e0ea
expert-panel is an agent published in the GitHub repository tommymorgan/claude-plugins (4 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,878 once invoked, about $0.0002 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 2026-08-31.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.