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 agentmods add skills/devdannnny/chisel/seo-nextnpx skills add Devdannnny/chisel --skill seo-nextgit clone --depth 1 https://github.com/Devdannnny/chiselWhat 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 | $0.00184 | $0.03022 |
| Opus 5 | $0.00092 | $0.01511 |
| Sonnet 5 | $0.00037 | $0.00604 |
| Haiku 4.5 | $0.00018 | $0.00302 |
Grade A, and why
seo-next 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 2d 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO — Next.js
Ship Next.js sites that score 100/100 against a Neil-Patel-grade technical + on-page SEO rubric. This skill encodes a weighted, auditable scoring model (adapted from the SEOmator seo-audit-skill, https://github.com/seo-skills/seo-audit-skill) and maps every check to a concrete Next.js implementation. Built on the Prompt Architecture Standard (PAS) — see skills/prompt-architect/. For the visual/UI layer, pair with ../frontend/next/SKILL.md.
Role
You are a senior technical SEO engineer who ships Next.js. You think in the App Router Metadata API first, you treat Core Web Vitals as a ranking factor not an afterthought, and you never ship a page without canonical, structured data, and an OG image. You measure before and after — a score with no evidence is a guess.
Objective
Take a Next.js app from its current state to 100/100 on the rubric in checklist.md, with every point backed by a real file change or a measured metric — not a claim. The deliverable is working code plus a scored report, not advice.
The scoring model (100 points)
Nine weighted domains. Full per-item rubric in checklist.md. A page is not "done" until every domain is green or the user has explicitly waived a line item.
| Domain | Weight | What it covers |
|---|---|---|
| Meta Tags | 15 | Title, description, canonical, viewport, robots directives, title templates |
| Technical SEO | 15 | robots.ts, sitemap.ts, clean URLs, status codes, redirects, indexability |
| Core Web Vitals | 15 | LCP, CLS, INP, FCP, TTFB — measured, not assumed |
| Security | 10 | HTTPS, HSTS, CSP, secure response headers |
| Links | 10 | No broken links, descriptive anchors, sane internal-link depth |
| Images | 10 | next/image, alt text, explicit dimensions, modern formats |
| Headings | 10 | Exactly one <h1>, logical hierarchy, no skipped levels |
| Structured Data | 8 | Valid JSON-LD (Organization, Article, Product, BreadcrumbList, FAQ…) |
| Social | 7 | Open Graph + Twitter cards, OG image per route |
What ships with it
1 file 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.
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.
- 2d ago First seen · 229 lines · 184 tokens per session scan A bf291bc71ae4
seo-next is a skill published in the GitHub repository Devdannnny/chisel (3 stars, last pushed 2mo ago), licensed MIT. It adds 184 tokens to every session and 3,022 once invoked, about $0.0009 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
copywriter
Use when writing landing page copy, app store descriptions, onboarding flows, email sequences, push notifications, or any user-facing text.
banner-design
Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist…
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
oh-my-opencode-slim
Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt improvement.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.