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/bengous/claude-code-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/bengous/claude-code-plugins/pinpoint)<a href="https://agentmods.dev/plugins/bengous/claude-code-plugins/pinpoint"><img src="https://agentmods.dev/badge/plugins/bengous/claude-code-plugins/pinpoint/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/bengous/claude-code-plugins/pinpoint"><img src="https://agentmods.dev/badge/plugins/bengous/claude-code-plugins/pinpoint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pinpoint 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 today.
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": "pinpoint",
"version": "0.5.0",
"description": "Point at your running app and talk to Claude: the session's address serves the app with an overlay that picks an element by a click or a zone by a drag, takes a quick label or a note, and keeps each selection in a batch you send at once; the batch reaches the session as a prompt, each element described by its selector, role, accessible name, box and styles, each zone with an image of it",
"author": {
"name": "Augustin BENGOLEA",
"email": "[email protected]"
},
"homepage": "https://github.com/bengous/claude-code-plugins/tree/main/pinpoint",
"repository": "https://github.com/bengous/claude-code-plugins",
"license": "MIT",
"keywords": ["browser", "overlay", "dev-server", "proxy", "feedback", "mod", "function-hooks"]
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 83 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.
- today Changed a2def7affa4f
- yesterday First seen · 14 lines scan A ef444253be46
pinpoint is a plugin published in the GitHub repository bengous/claude-code-plugins (5 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 2026-10-19.
Other plugins, from other repositories
browser
Browser automation for agents on top of the playwright-cli CLI (@playwright/cli): drive pages, hand the user a headed window, put a feedback toolbar on a dev page, pick elements.
browser-tools
Chrome automation tools for agent-assisted web testing and interaction using Chrome DevTools Protocol.
build-information
MCP configuration declaring 1 server: build-information.
kiln
Multi-model software creation pipeline. A conversation becomes running, tested software — an interactive brainstorm, then an autonomous build: GPT-5.6 writes the code, Claude shapes the plans and interfaces, and each family inspects the work of the other.
kit
Spec-driven Claude Code workflow with verification pipeline. Hooks, slash commands, and verification subagents.
moderncss
Opinionated rules for modern CSS, so agents and people write it consistently.