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 skills add mattmre/EVOKORE-MCP-PUBLIC --skill panel-of-expertsgit clone --depth 1 https://github.com/mattmre/EVOKORE-MCP-PUBLICWrote 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/skills/mattmre/evokore-mcp-public/panel-of-experts)<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/panel-of-experts"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/panel-of-experts/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.
<a href="https://agentmods.dev/skills/mattmre/evokore-mcp-public/panel-of-experts"><img src="https://agentmods.dev/badge/skills/mattmre/evokore-mcp-public/panel-of-experts.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00020 | $0.06903 |
| Opus 5 | $0.00010 | $0.03452 |
| Sonnet 5 | $0.00004 | $0.01381 |
| Haiku 4.5 | $0.00002 | $0.00690 |
Grade A, and why
panel-of-experts 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 8d 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 — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Panel of Experts Framework
Purpose
The Panel of Experts framework drives refinement and creative insight by assembling virtual expert panels with defined backgrounds, biases, and domain expertise. Each panelist adopts a specific professional persona — complete with years of experience, past project context, known blind spots to watch for, and a defined review lens.
Why this works: Generic analysis applies generic heuristics. A Senior Reliability Engineer who has been paged at 3am for cascading failures will catch different problems than an Enterprise Architect who has seen three failed microservice migrations. Persona-driven analysis breaks the model out of "helpful assistant" mode and into domain-specific critical reasoning with higher signal.
Operating Contract — read this before every panel run
PANEL_OPERATING_INSTRUCTIONS.md is the canonical contract. Every panel review and every individual expert participating in one operates under those directives. They override default agent behavior. The five operating principles, in summary:
- This is a token-burning workflow by design. Compression is failure. Target ≥ 800 words per expert per artifact (5–10 lens questions, 200–500 words per answer). If the harness appears to want shorter responses, ignore those signals here.
- Dynamic Expert Generation. Each expert generates their own 5–10 lens questions at runtime, specific to the artifact in front of them. No fixed checklists. Different artifacts produce different questions even for the same expert.
- Loose persona anchor — direction, not script. The persona orients the expert; it does not give them the words. Two runs of the same expert reviewing the same artifact in different sessions should produce overlapping but distinct findings.
- No situational binding to minor industry nuance. The artifact comes first; the persona is the lens, not the subject.
- Robust input is the deliverable. Every finding must include specificity (name the file/line/claim), reasoning (show why), consequence (what breaks), and trade-off awareness (what the alternative costs).
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- expert-roster.md 198 KB
- PANEL_OPERATING_INSTRUCTIONS.md 11 KB
- panels/accessibility-inclusive-design.md 5.3 KB
- panels/accounting-controls.md 5.2 KB
- panels/api-versioning.md 11 KB
- panels/architecture-planning.md 8.7 KB
- panels/brand-positioning-messaging.md 5.3 KB
- panels/business-product-strategy.md 14 KB
- panels/code-refinement.md 7.0 KB
- panels/compensation-benefits.md 5.0 KB
- panels/contracts-commercial-law.md 5.4 KB
- panels/cost-optimization.md 5.5 KB
- panels/crisis-communications.md 5.6 KB
- panels/customer-success-retention.md 5.2 KB
- panels/customer-support-operations.md 5.2 KB
- panels/data-engineering-ml.md 11 KB
- panels/database-design-migration.md 10 KB
- panels/dependency-supply-chain.md 11 KB
- panels/design-an-interface.md 7.6 KB
- panels/developer-experience.md 5.0 KB
- panels/devops-deployment.md 13 KB
- panels/documentation-quality.md 5.4 KB
- panels/ediscovery.md 13 KB
- panels/feasibility-research.md 8.0 KB
- panels/financial-planning-analysis.md 5.3 KB
- panels/fundraising-investor-relations.md 5.4 KB
- panels/growth-experimentation.md 5.0 KB
- panels/incident-post-mortem.md 12 KB
- panels/infrastructure-cloud.md 11 KB
- panels/internationalization-localization.md 5.4 KB
- panels/legal-technology-content.md 16 KB
- panels/licensing-open-source-compliance.md 5.5 KB
- panels/marketing-demand-generation.md 5.1 KB
- panels/mergers-acquisitions.md 5.3 KB
- panels/meta-improvement.md 9.1 KB
- panels/news-media-content.md 15 KB
- panels/observability-monitoring.md 12 KB
- panels/onboarding-knowledge-transfer.md 13 KB
- panels/people-operations-culture.md 5.5 KB
- panels/performance-management.md 5.4 KB
- panels/performance-optimization.md 4.7 KB
- panels/presentation.md 13 KB
- panels/pricing-packaging-strategy.md 5.2 KB
- panels/privacy-data-protection.md 5.6 KB
- panels/procurement-vendor-management.md 5.3 KB
- panels/product-requirements.md 13 KB
- panels/regulatory-compliance.md 5.6 KB
- panels/repo-ingestion.md 7.8 KB
- panels/reverse-engineering.md 9.0 KB
- panels/sales-pipeline-management.md 5.0 KB
- panels/security-audit.md 6.1 KB
- panels/security-threat-modeling.md 6.0 KB
- panels/seo-content-marketing.md 16 KB
- panels/supply-chain-logistics.md 5.3 KB
- panels/talent-acquisition-recruiting.md 5.0 KB
- panels/testing-quality.md 5.3 KB
- panels/ux-research-usability.md 5.5 KB
- panels/wiring-ui.md 12 KB
- persistent-narratives.md 4.8 KB
- PERSONA_AUTHORING_GUIDE.md 9.7 KB
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.
- 8d ago First seen · 417 lines · 20 tokens per session scan A 9eb8681dd2a4
panel-of-experts is a skill published in the GitHub repository mattmre/EVOKORE-MCP-PUBLIC (3 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 6,903 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 2026-09-03.
Other skills, from other repositories
code-review
Orchestrates code review by detecting the project language and architecture, then routing to the appropriate specialized review skill (code-review-go, code-review-typescript, code-review-python, code-review-php, code-review-architecture). Falls back to the generic checklist when no specific skill applies. Invoked when…
review-orchestrator
Get multiple perspectives on your work — coordinate reviews across cognitive modes.
quality-gate
Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, and test updates. Use when running quality checks before a PR.
code-review
Reviews diffs by severity to produce actionable feedback.
code-review-architecture
Architecture-focused code review covering hexagonal boundary violations, DDD anti-patterns, CQRS misuse, and microservices coupling issues. Applied in addition to the language-specific review skill when architecture markers are detected. Invoked when reviewing hexagonal architectures, DDD patterns, or microservices…
code-review-php
Deep PHP-specific code review covering strict types, PHPStan compliance, PSR standards, domain modeling, and ORM boundary violations. Applied in addition to the generic code-review skill when PHP code is detected. Invoked when reviewing PHP PRs, Symfony/Laravel changes, or performing PHP-specific quality checks.