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/clay-run/agent-pluginsWrote 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/clay-run/agent-plugins/clay)<a href="https://agentmods.dev/plugins/clay-run/agent-plugins/clay"><img src="https://agentmods.dev/badge/plugins/clay-run/agent-plugins/clay/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/clay-run/agent-plugins/clay"><img src="https://agentmods.dev/badge/plugins/clay-run/agent-plugins/clay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
clay 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What it installs
The manifest is a name and a version. 35 skills travel with it, and installing the plugin installs all of them — 2,069 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill signals A 83 tokens
- Skill workflows A 31 tokens
- Skill audiences A 90 tokens
- Skill clay A 142 tokens
- Skill schedules A 65 tokens
- Skill routines A 86 tokens
- Skill searches A 43 tokens
- Skill tables-cli A 69 tokens
- Skill workflows-discover-actions A 42 tokens
- Skill workflows-snapshots A 40 tokens
- Skill ad-syncs A 66 tokens
- Skill tables-error-sweep A 55 tokens
- Skill workflows-audience-enrichment A 47 tokens
- Skill workflows-campaign-enrollment A 51 tokens
- Skill clay-docs A 66 tokens
- Skill onboard A 98 tokens
- Skill tables-analyze A 67 tokens
- Skill tables-trace A 66 tokens
- Skill tables-value-trace A 67 tokens
- Skill workflows-inbound-lead-routing A 52 tokens
- Skill credits-quotas-plans A 64 tokens
- Skill tables-capacity A 53 tokens
- Skill workflows-claygent A 62 tokens
- Skill workflows-optimize-credits A 38 tokens
- Skill workflows-vs-tables A 82 tokens
- Skill cli A 78 tokens
- Skill update A 72 tokens
- Skill workflows-simplify A 41 tokens
- Skill campaigns-interview A 26 tokens
- Skill campaigns-sequence-reviewing A 24 tokens
- Skill clay-feedback A 27 tokens
- Skill campaigns-sequence-writing A 22 tokens
- Skill public-api A 34 tokens
- Skill campaigns B 25 tokens
- Skill setup C 95 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 4f94c43cd6c7
- 10d ago Changed 40c151b4096b
- 14d ago Changed 16286491b4e1
- 15d ago Changed c55c492c71d8
- 21d ago Changed 196b9fcf65df
- 24d ago Changed · +13 lines 89171d469bef
- 25d ago Changed 8da8714a38b4
- 29d ago Changed dc88dad5325e
- 1mo ago Changed d3c98ec506e7
- 1mo ago First seen · 29 lines scan A 6f5681e23a79
clay is a plugin published in the GitHub repository clay-run/agent-plugins (138 stars, last pushed 2d ago), with no licence file. 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
pad
Talk to your project. Pad is local-first project management for developers and AI agents — this plugin gives Claude Code a conversational Pad skill, typed shortcuts (/pad:status, /pad:capture, /pad:onboard, /pad:connect, /pad:disconnect), a /pad-pane side panel for browsing and updating your workspace, and…
personal
Personal knowledge and finance automation — autonomous Obsidian vault management (PARA + LLM Wiki) and end-to-end corporate/personal tax preparation from Xero, bank statements, and Google Drive.
skills
Skill discovery, installation, and authoring — find skills with scout, create new universal skills with skill-builder.
skillreaper
Measures what share of your agent's loaded context is ever actually invoked - skills, MCP servers, subagents, hooks, always-loaded prose - using evidence from your own session transcripts. Then prunes the dead weight, reversibly.
happyhackingspace-skills
Provides access to the Happy Hacking Space Skills.
shield-kya
Audit trail and traceability for AI agents. See what every coding agent did. Advisory: records every tool call, blocks only the never-list, fails open.