expert-panel

expert-panel is a skill for Claude Code from t1djani/servo. It costs 54 tokens per session (898 once invoked), scanned A, original, MIT.

A decision-making workflow that brings together a small group of relevant domain specialists, including one assigned dissenter, when there is no established answer to an architecture or design choice. A human then chooses among the considered options.

In plain words
What is it for?
Use it for genuine design forks, such as architecture decisions or competing approaches that cannot be settled by existing requirements or evidence. It helps frame the choice, compare options, challenge them, and present a synthesis for human approval.
Why use it?
It reduces the risk of one agent selecting the first plausible solution with unwarranted confidence. The dissenter is included to expose weaknesses and hidden trade-offs.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; names the TodoWrite tool.

Part of the servo plugin — 9 skills, 1 command shipped together

Good fit Use it for genuine design forks, such as architecture decisions or competing approaches that cannot be settled by existing requirements or evidence. It helps frame the choice, compare options, challenge them, and present a synthesis for human approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/t1djani/servo/expert-panel
Install

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.

Any agent
npx skills add t1djani/servo --skill expert-panel
Clone the repo
git clone --depth 1 https://github.com/t1djani/servo

Made for: Claude Code.

Or install servo, the plugin that ships this one along with the rest of its 9 skills, 1 command.

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/t1djani/servo/expert-panel.svg)](https://agentmods.dev/skills/t1djani/servo/expert-panel)
Your own site
<a href="https://agentmods.dev/skills/t1djani/servo/expert-panel"><img src="https://agentmods.dev/badge/skills/t1djani/servo/expert-panel.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 898 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 $0.00054 $0.00898
Opus 5 $0.00027 $0.00449
Sonnet 5 $0.00011 $0.00180
Haiku 4.5 $0.00005 $0.00090

Measured 7d ago against content hash 303c1811d765, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 7d 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.

skills/expert-panel/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

expert-panel

A good brainstorm is several experts, each master of a domain, who bring their knowledge and argue toward a decision. Use this when a choice has no ground truth to check against yet — a design fork, an architecture call, a tradeoff. For anything that can be checked against an oracle, use servo-gate instead; this skill is for generating and stress-testing options, not verifying them.

The failure this prevents: one model picking the first plausible option with false confidence, and a panel of same-context models agreeing with each other.

Keep it visible: open a TodoWrite list with one todo per expert (plus the dissenter and the synthesis), and mark each in_progress/completed as it reports. The human should see the panel convene and resolve, not wait on a silent block.

Procedure

  1. Frame the fork. State the decision and the constraints from the context brief (gather-context). If there is genuinely an oracle that settles it, stop — this is a gate, not a panel.

  2. Convene the MINIMAL relevant set — usually 2-3, not every plausibly-related domain. From the manifest's experts, pick only the ones the decision genuinely turns on (a data fork wakes the data expert; it does not need the bot expert). Convening six experts on a three-expert problem is the waste this step must avoid.

    How to spawn an expert: an expert is not a named agent type — do not try to spawn an agent called data or hs-coaching (it does not exist and will fail). Spawn a plain general subagent and give it the expert's identity as context: the expert's sources from the manifest (read any skill: pointer as a file, read the listed code/notes), plus the context brief from gather-context, plus its assigned stance. That content IS the expert. Hand it the brief so it does not re-read the whole project — it only goes deeper into its own slice. Each expert is a real, separate perspective — not you role-playing all of them. These reader-experts can run on a cheaper, faster model; reserve the strong model for the synthesis in step 5.

Read the full file on GitHub · 40 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. 7d ago First seen · 40 lines · 54 tokens per session scan A 303c1811d765

Subscribe to this mod's changes

expert-panel is a skill published in the GitHub repository t1djani/servo (1 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 898 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 2026-08-31.

Related

Other skills, from other repositories

quiz-me

Quiz the user on root cause and intended fix BEFORE writing any non-trivial code, then verify comprehension of every change after. Use when the user asks for a bug fix, refactor, or feature and wants to stay technically sharp instead of vibe-coding. Also use when the user says "quiz me", "don't let me vibe code", or…

emanzurv/quiz-me-skill · 82 tokens

website-deploy-builder

Plan what to build on Website Deploy (simple-host.app). Helps a user decide whether their idea fits the static + light-backend model, maps it to concrete patterns (shared JSON state with atomic ops, append-only collections, localStorage, public APIs), and produces a focused prompt for an implementation agent. Knows…

vineetu/simple-host · 128 tokens

connect-domain

Connect a user's own custom domain (subdomain e.g. recipes.brand.com via CNAME, or apex e.g. brand.com via A record) to a site already deployed on simple-host. Use when a user wants their site served from their own domain over HTTPS, or wants sign-in on saves from a page (a domain is what adds sign-in to saves; on the…

vineetu/simple-host · 119 tokens

craft

Engineering standards for any code work on any stack — writing production code, slicing and reviewing PRs, authoring tests, running gates, merging, and running agent fleets. Load before touching code, not after review flags it.

abhimanyusingh-gh/software-craftsmanship · 47 tokens

personal-voice-capture

Use when a user wants an agent to learn, encode, or improve their personal writing voice as a reusable skill through source-text ingestion and iterative calibration edits.

eranshir/personal-voice-capture · 37 tokens

demo-video-factory

Generate a custom 26s product-demo video from any SaaS URL — brand-matched scenes, a recreated product-UI "wow" scene, real screenshots, and a soundtrack. Use whenever the user wants a demo, promo, launch, or marketing video for a website or product.

jonny-1812/demo-video-factory · 63 tokens