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.
git clone --depth 1 https://github.com/Jeffallan/writing-with-agentsWrote 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/jeffallan/writing-with-agents/plugin)<a href="https://agentmods.dev/plugins/jeffallan/writing-with-agents/plugin"><img src="https://agentmods.dev/badge/plugins/jeffallan/writing-with-agents/plugin/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/plugins/jeffallan/writing-with-agents/plugin"><img src="https://agentmods.dev/badge/plugins/jeffallan/writing-with-agents/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
writing-with-agents 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 yesterday.
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": "writing-with-agents",
"version": "0.3.2",
"description": "10 specialized writing skills implementing Betty Flowers' Madman-Architect-Carpenter-Judge framework with Bryan Garner's whirlybird technique, SEO optimization, quality rubric, and multi-article content strategy. Features collaborative oscillation between AI and human across all phases.",
"author": {
"name": "jeffallan",
"email": "[email protected]",
"url": "https://github.com/jeffallan"
},
"homepage": "https://jeffallan.github.io/writing-with-agents/",
"documentationUrl": "https://jeffallan.github.io/writing-with-agents/",
"supportUrl": "https://github.com/Jeffallan/writing-with-agents/issues",
"privacyPolicyUrl": "https://jeffallan.github.io/writing-with-agents/privacy/",
"license": "MIT",
"repository": "https://github.com/Jeffallan/writing-with-agents",
"keywords": [
"claude-skill",
"claude-code",
"writing",
"content-strategy",
"seo",
"flowers-method",
"whirlybird",
"technical-writing",
"nonfiction",
"editing",
"quality-rubric",
"research",
"knowledge-management",
"model-invoked"
],
"skills": "./skills/",
"commands": {
"flowers-cycle": {
"source": "./commands/writing/flowers-cycle/COMMAND.md"
},
"content-strategy": {
"source": "./commands/writing/content-strategy/COMMAND.md"
},
"capture": {
"source": "./commands/capture/COMMAND.md"
},
"writing-setup": {
"source": "./commands/utilities/writing-setup/COMMAND.md"
},
"human-voice": {
"source": "./commands/utilities/human-voice/COMMAND.md"
}
}
}
What it installs
The manifest is a name and a version. 10 skills travel with it, and installing the plugin installs all of them — 368 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill carpenter A 31 tokens
- Skill content-strategist A 42 tokens
- Skill judge A 33 tokens
- Skill quality-rubric A 36 tokens
- Skill research-intake A 37 tokens
- Skill seo-writer A 33 tokens
- Skill architect A 38 tokens
- Skill knowledge-harvester A 38 tokens
- Skill madman A 41 tokens
- Skill whirlybird A 39 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.
- yesterday Changed · +3 lines 6b52c9fca990
- 10d ago First seen · 48 lines scan A 38cdbbf0c276
writing-with-agents is a plugin published in the GitHub repository Jeffallan/writing-with-agents (34 stars, last pushed today), licensed MIT. 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 2026-10-06.
Other plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.