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 2389-research/review-squad --skill expertsgit clone --depth 1 https://github.com/2389-research/review-squadWrote 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/2389-research/review-squad/experts)<a href="https://agentmods.dev/skills/2389-research/review-squad/experts"><img src="https://agentmods.dev/badge/skills/2389-research/review-squad/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/2389-research/review-squad/experts"><img src="https://agentmods.dev/badge/skills/2389-research/review-squad/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 | $0.00042 | $0.01999 |
| Opus 5 | $0.00021 | $0.01000 |
| Sonnet 5 | $0.00008 | $0.00400 |
| Haiku 4.5 | $0.00004 | $0.00200 |
Grade A, and why
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 9d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expert Panel
Overview
Dispatch a panel of expert reviewer subagents in parallel to audit a project. Each agent adopts a specialist persona and reviews independently. Results are consolidated into a single severity-ranked report that feeds into an implementation plan.
When to Use
- Pre-launch review ("ready to go live?")
- Post-refactor audit ("did we break anything?")
- Inherited codebase assessment ("what are we working with?")
- Periodic health check
- Any project type: web, mobile, API, CLI, infrastructure, data pipeline
Workflow
digraph expert_review {
rankdir=TB;
"User requests review" -> "Identify project type";
"Identify project type" -> "Present default panel for that type";
"Present default panel for that type" -> "Suggest stack-specific additions";
"Suggest stack-specific additions" -> "Ask: add, remove, or adjust?";
"Ask: add, remove, or adjust?" -> "Finalize panel";
"Finalize panel" -> "Dispatch all agents in parallel (run_in_background)";
"Dispatch all agents in parallel (run_in_background)" -> "As each completes, note key finding";
"As each completes, note key finding" -> "All done?";
"All done?" -> "As each completes, note key finding" [label="no"];
"All done?" -> "Consolidate into severity-ranked table" [label="yes"];
"Consolidate into severity-ranked table" -> "Present full report";
"Present full report" -> "Offer to write implementation plan for fixes";
}
Default Panels by Project Type
Web (static sites, SPAs, server-rendered apps)
| # | Expert | Focus Areas |
|---|---|---|
| 1 | SEO Expert | Meta tags, heading hierarchy, sitemap, robots.txt, URL structure, RSS, structured data |
| 2 | Accessibility Expert | Semantic HTML, skip nav, ARIA, color contrast, keyboard nav, motion/animation |
| 3 | Mobile UX Expert | Viewport, responsive CSS, touch targets (44x44px min), font sizes, overflow |
| 4 | Copy Editor | Spelling, grammar, tone consistency across all templates and content |
| 5 | Performance Expert | CSS/JS delivery, image optimization, fonts, caching, build config |
| 6 | Security Reviewer | Headers, XSS vectors, sensitive data exposure, link security, CORS |
| 7 | Social/Meta Tags Specialist | OpenGraph, Twitter cards, favicon, canonical URLs, share previews |
| 8 | Web Standards Expert | HTML validation, correct element usage, spec compliance, ARIA misuse |
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.
- 9d ago First seen · 186 lines · 42 tokens per session scan A eab91f731ca4
experts is a skill published in the GitHub repository 2389-research/review-squad (12 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 1,999 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 skills, from other repositories
pr
Use when reviewing an incoming GitHub pull request — runs the multi-level (L1-L5) audit against the PR's real diff range, posts findings as one batched review (inline, summary, or local-only), offers the standard fix chain on NEEDSFIX, and optionally merges. The maintainer-side counterpart to /hyperflow:issue. Trigger…
deep-security-audit
Multi-agent deep security audit — 6 expert personas (pentester, architect, code auditor, supply chain, data privacy, forensics) + CISO synthesis + optional fix implementation.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
agent-review
Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
link-check
Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix.