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/robertguss/claude-code-toolkitWrote 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/robertguss/claude-code-toolkit/compound-writing)<a href="https://agentmods.dev/plugins/robertguss/claude-code-toolkit/compound-writing"><img src="https://agentmods.dev/badge/plugins/robertguss/claude-code-toolkit/compound-writing/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/robertguss/claude-code-toolkit/compound-writing"><img src="https://agentmods.dev/badge/plugins/robertguss/claude-code-toolkit/compound-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
compound-writing 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 1mo 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": "compound-writing",
"version": "1.0.0",
"description": "AI-powered writing tools that compound your writing skills. Includes 7 specialized agents, 4 workflow commands, and 5 skills for research, drafting, editing, and voice consistency.",
"author": {
"name": "Kieran Klaassen",
"email": "[email protected]",
"url": "https://github.com/kieranklaassen"
},
"homepage": "https://every.to",
"repository": "https://github.com/EveryInc/every-marketplace",
"license": "MIT",
"keywords": [
"ai-powered",
"compound-writing",
"writing-automation",
"voice-consistency",
"editorial",
"content-creation",
"style-guides",
"writing-workflow"
]
}
What it installs
The manifest is a name and a version. 5 skills, 4 commands, 7 agents travel with it, and installing the plugin installs all of them — 1,164 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill dhh-writing A 56 tokens
- Skill voice-capture A 45 tokens
- Skill writing-orchestration A 60 tokens
- Skill pragmatic-writing A 62 tokens
- Skill every-style-editor A 44 tokens
- Command writing:compound A 14 tokens
- Command writing:draft A 12 tokens
- Command writing:plan A 15 tokens
- Command writing:review A 13 tokens
- Agent clarity-editor A 123 tokens
- Agent publishing-optimizer A 132 tokens
- Agent source-researcher A 136 tokens
- Agent structure-architect A 124 tokens
- Agent voice-guardian A 126 tokens
- Agent fact-checker A 112 tokens
- Agent every-style-editor A 90 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.
- 1mo ago First seen · 24 lines scan A 6a856e8f4688
compound-writing is a plugin published in the GitHub repository robertguss/claude-code-toolkit (126 stars, last pushed 1mo ago), 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 2026-08-30.
Other plugins, from other repositories
agentic-workflow
Stack-agnostic agent skills for a disciplined, doc-driven feature/issue workflow: design, plan, execute by phases, review, audit, and ship — with a full internal review pack and merge gates.
ism
Expert Australian Information Security Manual (ISM) advisor for Australian government entities, contractors and supply chains. Gap analysis, system authorisation, IRAP preparation, control scoping, and ASD compliance guidance.
casely
Virtual QA lead: turns requirements into TestRail-ready test cases in one conversation, plus a runnable Postman collection when the spec describes an API.
hyperclaude
Push Claude Code beyond stock. Skills, agents, Codex collab — opinionated and personal.
context-optimization
Techniques for extending effective context capacity through compaction, observation masking, KV-cache optimization, and context partitioning. Double or triple effective context without larger models.
adapto
Operate Adapto CMS from your AI coding agent — a content studio: scaffold sites, build project context, and research, write, translate, and publish on-brand SEO content via the adapto CLI.