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 well-actuallygit 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/well-actually)<a href="https://agentmods.dev/skills/2389-research/review-squad/well-actually"><img src="https://agentmods.dev/badge/skills/2389-research/review-squad/well-actually/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/well-actually"><img src="https://agentmods.dev/badge/skills/2389-research/review-squad/well-actually.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 | $0.00061 | $0.01629 |
| Opus 5 | $0.00030 | $0.00814 |
| Sonnet 5 | $0.00012 | $0.00326 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
well-actually 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 11d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Well, Actually...
Overview
Dispatch a panel of insufferably pedantic subagents who each obsess over a different domain. They nitpick everything — typography crimes, grammar sins, standards violations, questionable tech choices, inconsistent pixels. The value is catching the small things that professional reviewers skip but opinionated people on the internet will absolutely roast you for.
This is NOT a professional audit. The review-squad:experts skill gives you structured, severity-ranked findings. This skill gives you the feedback you'd get if your site hit the front page of Hacker News.
When to Use
- Before launching anything public ("what will people roast me for?")
- After you think you're done ("what did I miss?")
- When you want that last 5% of polish
- When you need motivation to fix the things you've been ignoring
The Default Panel (6 Pedants)
Present this to the user before dispatching. They may adjust.
| # | Persona | Their Obsession | Reviews |
|---|---|---|---|
| 1 | The Typographer | Font pairing, kerning, line-height, orphans/widows, vertical rhythm | Rendered site + CSS |
| 2 | The Grammarian | Every comma, dash, capitalization inconsistency, passive voice | Rendered text only |
| 3 | The Standards Zealot | Semantic HTML, valid markup, ARIA correctness, spec compliance | Rendered DOM + templates |
| 4 | The HN Commenter | Tech choices, bundle size, over-engineering, "why not plain HTML?" | Source code + rendered site |
| 5 | The Pixel Cop | Inconsistent spacing, mismatched border-radii, colors off by one shade | Rendered site + CSS |
| 6 | The UX Reply Guy | "As a UX professional..." — hover states, transitions, click targets, flow | Rendered site |
Suggest additions based on the project. E-commerce? Add "The Checkout Critic." API? Add "The REST Pedant." Open source? Add "The License Lawyer."
Code Access Rules
Unlike normies and regulars (where agents must be cold visitors), pedants access what their persona naturally would:
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.
- 11d ago First seen · 148 lines · 61 tokens per session scan A 5da390eb66ab
well-actually is a skill published in the GitHub repository 2389-research/review-squad (12 stars, last pushed 2mo ago), licensed MIT. It adds 61 tokens to every session and 1,629 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.
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…
aesthetic-instrument
A committed aesthetic in the sense of skills/committed-aesthetic/SKILL.md: every rule below is checkable, and every value was read out of the source — packages/board/public/index.html and greatcto-site/styles.css — rather than chosen to write this document.
committed-aesthetic
How to write — and how to use — a skill that IS one aesthetic rather than a catalogue of them. A catalogue lets an agent pick, and it picks the modal option; a committed aesthetic makes it execute one thing precisely, against rules you can check. Use when a design keeps coming out competent and forgettable, when…
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
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.
apple-hig-check
Audit code or design against Apple Human Interface Guidelines.