expert-panel

expert-panel is a skill for Claude Code from ondrej-svec/heart-of-gold-toolkit. It costs 94 tokens per session (6,066 once invoked), scanned A, original, MIT.

A structured review method that examines content through several named analytical frameworks, such as learning science or software design. It researches the frameworks' published sources and combines the findings into one set of recommendations.

In plain words
What is it for?
Use it to review writing, product ideas, or other content from multiple perspectives, identify common findings, and produce a prioritized action list.
Why use it?
It replaces vague expert-role imitation with traceable ideas from real sources and shows where different forms of analysis agree or disagree.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the deep-thought plugin — 11 skills, 9 agents shipped together

Good fit Use it to review writing, product ideas, or other content from multiple perspectives, identify common findings, and produce a prioritized action list.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ondrej-svec/heart-of-gold-toolkit
Claude Code
/plugin install deep-thought

Made for: Claude Code.

Or install deep-thought, the plugin that ships this one along with the rest of its 11 skills, 9 agents.

Wrote 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.

agentmods badge for expert-panel

README.md
[![agentmods](https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/expert-panel/github.svg)](https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/expert-panel)
Your own site
<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/expert-panel"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/expert-panel/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for expert-panel

Your own site · 80×15
<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/expert-panel"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/expert-panel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,066 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00094 $0.06066
Opus 5 $0.00047 $0.03033
Sonnet 5 $0.00019 $0.01213
Haiku 4.5 $0.00009 $0.00607

Measured 12d ago against content hash b119968a1f72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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 12d 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.

plugins/deep-thought/skills/expert-panel/SKILL.md · 518 lines

How it starts

The opening of the file, as written. The whole thing — 518 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expert Panel

Apply multiple analytical frameworks to content in parallel, then synthesize the findings into convergent signals, productive disagreements, and a prioritized action list.

What this skill is — and what it is not

Each lens is a named analytical framework (evolutionary design, learning science, practitioner reality-check, etc.) with traceable sources (books, articles, published talks). The skill applies those frameworks to the target content and cites specific concepts by name.

Each lens is NOT a persona impersonation. The skill never claims "Fowler says" or "Newport would argue." It claims "applying the evolutionary-design framework (source: Fowler, Refactoring 2nd ed.) to this content, the following pattern emerges." The framework is the lens. The author is the source. The AI is the reader applying the framework — like a careful graduate student who read the book, not like the author in the room.

This distinction matters because:

  • AI cannot faithfully represent what a specific person thinks. It can apply their published frameworks.
  • Persona impersonation fabricates opinions and creates false authority. Framework application is traceable and falsifiable.
  • If a framework produces a wrong finding, you can check it against the source material. If a persona produces a wrong finding, there's nothing to check — it's just plausible-sounding noise.

Grounding tiers

The skill supports three tiers of grounding, from highest to lowest fidelity:

Tier 1 — User-provided reference material (highest fidelity)

The user provides the actual source texts (book chapters, blog posts, talk transcripts, papers) in a references/ directory or via --references <path>. Each lens reads its assigned reference material as primary context and applies the specific arguments from that material to the target content.

This is the closest to "what would the framework's author think" because the model is reading and applying THEIR actual words, not reconstructing them from training data. Citations point to specific sections of the provided material.

Read the full file on GitHub · 518 lines

Changes

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.

  1. 12d ago First seen · 518 lines · 94 tokens per session scan A b119968a1f72

Subscribe to this mod's changes

expert-panel is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 94 tokens to every session and 6,066 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens