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.
/plugin marketplace add stonegiantstudio/skillsnpx agentmods add plugins/stonegiantstudio/skills/stone-giantgit clone --depth 1 https://github.com/stonegiantstudio/skillsWrote 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/plugins/stonegiantstudio/skills/stone-giant)<a href="https://agentmods.dev/plugins/stonegiantstudio/skills/stone-giant"><img src="https://agentmods.dev/badge/plugins/stonegiantstudio/skills/stone-giant.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
stone-giant 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 5d 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.
What it actually says
{
"name": "stone-giant",
"description": "Production-tested skills from Stone Giant Studio — artifact scoring, shutdown rituals, npm evaluation and security, CI/CD speedups, React Router v7, JavaScript/TypeScript, PostgreSQL/SQL Server/Drizzle/Kysely databases, testing, UI design, auth, AWS serverless, PDF generation, technical and marketing writing, product strategy, and search/AI-answer visibility (SEO/GEO/AEO)",
"version": "1.4.0",
"author": {
"name": "Stone Giant Studio",
"url": "https://stonegiantstudio.com"
},
"repository": "https://github.com/stonegiantstudio/skills",
"license": "Apache-2.0",
"keywords": [
"productivity",
"code-quality",
"npm",
"security",
"developer-tools",
"ci-cd",
"react",
"react-router",
"typescript",
"testing",
"design",
"database",
"postgresql",
"sql-server",
"aws",
"pdf",
"writing",
"product-management",
"auth",
"seo",
"geo",
"aeo"
]
}
What it installs
The manifest is a name and a version. 36 skills travel with it, and installing the plugin installs all of them — 2,486 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill sql-server-performance A 64 tokens
- Skill lambda A 85 tokens
- Skill seo-geo-aeo A 156 tokens
- Skill signup-signin A 102 tokens
- Skill kysely-orm A 42 tokens
- Skill relational-db-theory A 50 tokens
- Skill sql-server A 49 tokens
- Skill zod-ninja A 55 tokens
- Skill dates-and-times A 70 tokens
- Skill js-ninja A 108 tokens
- Skill park A 45 tokens
- Skill pdf-create A 38 tokens
- Skill postgresql A 35 tokens
- Skill react-router-v7 A 110 tokens
- Skill better-auth A 59 tokens
- Skill eval-npm A 37 tokens
- Skill pdf-charts A 39 tokens
- Skill refactoring-legacy A 68 tokens
- Skill score A 58 tokens
- Skill agent-operating-standard A 53 tokens
- Skill design-ninja A 66 tokens
- Skill drizzle-migrations A 35 tokens
- Skill pdf-extract A 42 tokens
- Skill resend A 55 tokens
- Skill sql-server-safety A 55 tokens
- Skill testing-ninja A 50 tokens
- Skill writing-markdown A 82 tokens
- Skill pdf A 38 tokens
- Skill agent-philosophy A 73 tokens
- Skill ci-performance A 85 tokens
- Skill human-writing A 184 tokens
- Skill writing-marketing-copy A 120 tokens
- Skill technical-writing A 99 tokens
- Skill zen-break B 40 tokens
- Skill product-wisdom B 85 tokens
- Skill npm-security-advisory D 54 tokens
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.
- 5d ago First seen · 36 lines scan A 76d2c982ab6e
stone-giant is a plugin published in the GitHub repository stonegiantstudio/skills (2 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
jira-pack
Issue-tracker pack: /jira-fix takes a ticket link of any type, verifies tracker access, classifies it as a defect or a change, reproduces the defect or writes a failing acceptance test for the change, routes the work to core executors, comments back with evidence and moves the ticket to the QA column. Opt-in; requires.
harnessay
Profile your Claude Code transcripts: context budget report, skill-promotion candidates, and a skill regression test harness. Local-only, stdlib-only.
es6kr
A collection of AI coding skills including TDD, commit management, dotfile sync, and more.
next-todo
Land one GitHub child issue as one pull request: choose the next child issue, review the plan to consensus, implement with red-green TDD, open a draft pull request, and drain review comments until CI is green.
whetstone
Engineering-craft skills that sharpen the edge: red-green TDD, flaky-test audit, pre-decision doubt review, merge-conflict resolution, skill linting, and a column budget computed from the staged diff. Each carries a deterministic self-verify.
superpowers-deepseek-v4
Superpowers DeepSeek v4: composable agent skills for TDD, debugging, and collaboration. Independently maintained; not identical to obra/superpowers.