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 DevZonayed/Mochinpx agentmods add plugins/devzonayed/mochi/marketplacegit clone --depth 1 https://github.com/DevZonayed/MochiGrade A, and why
mochi 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
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "mochi",
"description": "Mochi — a browser companion for AI assistants. Bundled browser automation, persistent project memory, and human-in-the-loop hint messaging.",
"owner": {
"name": "Jonayed Ahamed",
"email": "[email protected]"
},
"plugins": [
{
"name": "mochi",
"description": "Browser automation MCP + Continuum context-chain memory + in-page hint modal. Pair with the Mochi Chrome extension (⌘⇧M on any tab).",
"author": {
"name": "Jonayed Ahamed",
"email": "[email protected]"
},
"category": "development",
"tags": ["browser", "automation", "memory", "qa", "chrome", "mcp"],
"source": "./",
"homepage": "https://github.com/DevZonayed/Mochi"
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 24 lines scan A fcdcaf71da74
mochi is a plugin published in the GitHub repository DevZonayed/Mochi (3 stars, last pushed 15d 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 2026-08-31.
Other plugins, from other repositories
devharness
Run and debug a live app from inside Claude Code: breakpoints and variable inspection in Chrome and Node.js, managed dev servers, and replayable call history so setup is never re-driven by hand.
gettalon-talon-plugins
Plugin marketplace listing 9 plugins: talon, talon-web, hub, talon-computer-use, talon-autoresearch.
hub
Universal channel plugin for Claude Code with 21+ platform adapters. Connect via WebSocket (default) or use built-in adapters for Telegram, Discord, Slack, WhatsApp, Signal, iMessage, IRC, Google Chat, LINE, Feishu, Matrix, Mattermost, MS Teams, and more. Full hook event forwarding, permission relay, and bidirectional.
talon-adversarial-coding
GAN-style multi-agent coding — Planner, Generator, Evaluator work in adversarial loop. Inspired by Anthropic's research.
agent-factory
Create domain-specific AI agents, skills, and workflows. Build reusable agents for any domain — finance, security, DevOps, legal, documentation, and more.
talon-ai-dispatch
Dispatch subagents to multiple AI backends (GLM, Doubao, DeepSeek, Kimi, MiniMax). Simple: dispatch ark-code "prompt".