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/ma-ziwei/fathom-mode-for-claudeWrote 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/ma-ziwei/fathom-mode-for-claude/plugin)<a href="https://agentmods.dev/plugins/ma-ziwei/fathom-mode-for-claude/plugin"><img src="https://agentmods.dev/badge/plugins/ma-ziwei/fathom-mode-for-claude/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/ma-ziwei/fathom-mode-for-claude/plugin"><img src="https://agentmods.dev/badge/plugins/ma-ziwei/fathom-mode-for-claude/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
fathom 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": "fathom",
"version": "0.1.0",
"description": "Planning session mode for complex tasks. Enter Fathom Mode to build shared understanding through structured dialogue before execution. Use this when you want to plan, think through, or clarify something complex before acting on it.",
"author": {
"name": "Lawrence Ma"
},
"license": "MIT",
"keywords": ["planning", "intent", "clarification", "protocol", "agent-skills"],
"homepage": "https://github.com/ma-ziwei/fathom-mode-for-claude"
}
What it installs
The manifest is a name and a version. 1 skill, 4 commands, 1 hook travel with it, and installing the plugin installs all of them — 134 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 12 lines scan A f40daf040c34
fathom is a plugin published in the GitHub repository ma-ziwei/fathom-mode-for-claude (13 stars, last pushed 5mo 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
claw-hwp
Read, create, and edit Korean Hangul Word Processor documents (.hwp / .hwpx) in Claude. Built on the rhwp WebAssembly viewer/editor — no Hancom Office, no LibreOffice, no Windows COM required.
cowork-to-code-bridge
Connect Claude Cowork to Claude Code on your own computer (macOS or Linux). Cowork hands a task to a local Claude Code agent (and can run approved scripts too); the bridge is idempotent, streams progress, and is token-protected. Install with one command; it sets up a global Cowork skill so every session connects…
usetemi
Open-source agent skills from Temi for Claude Code, Claude Cowork, Codex, Cursor, and Gemini CLI.
fable-workflow
Fable-style agentic working method for any model — surface the unknowns before building on vague specs or unfamiliar code (blind-spot pass, interview, variants, log assumptions, stay in the loop).
memex
Structured memory for Claude Cowork. Tiered context loading, session automation, and Obsidian-compatible navigation.
graybeard
Universal engineering judgment for Claude Code. Read before editing, reuse before writing, verify before shipping.