A tool that counts repeated problems in a development setup and points out small fixes for symptoms that keep returning. It can check local configuration repositories and activity data such as command history and system logs.

Use it to find recurring slow commands, tool gaps, or setup conflicts and identify which small configuration fix is worth making.

It helps distinguish a one-off annoyance from friction that repeatedly wastes time. It keeps the proposed changes small instead of generating a long list of weak improvements.

friction — Plugin for Claude Code by bendrucker/claude

Install

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.

Clone the repo

git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/bendrucker/claude/friction/github.svg)](https://agentmods.dev/plugins/bendrucker/claude/friction)

Your own site

<a href="https://agentmods.dev/plugins/bendrucker/claude/friction"><img src="https://agentmods.dev/badge/plugins/bendrucker/claude/friction/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/bendrucker/claude/friction"><img src="https://agentmods.dev/badge/plugins/bendrucker/claude/friction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill cost 70 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

friction 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 19d 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.

plugins/friction/.claude-plugin/plugin.json · 31 lines

What it actually says

{
  "name": "friction",
  "description": "Count recurring friction across the development setup and surface only small fixes for symptoms that persist",
  "author": {
    "name": "Ben Drucker",
    "email": "[email protected]"
  },
  "dependencies": ["pull-request"],
  "userConfig": {
    "config_repos": {
      "type": "string",
      "multiple": true,
      "title": "Config repos",
      "description": "Local clones that hold the setup's config. A run checks each finding against them and opens its fixes there. Empty grounds findings against the config files the tools read.",
      "default": []
    },
    "osquery_dir": {
      "type": "string",
      "title": "osquery log directory",
      "description": "Directory holding osqueryd.snapshots.log. Empty uses ~/.local/state/osquery.",
      "default": ""
    },
    "atuin_db": {
      "type": "string",
      "title": "Atuin database",
      "description": "Path to Atuin's history.db. Empty uses ~/.local/share/atuin/history.db.",
      "default": ""
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 70 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Skill friction A 70 tokens

Changes

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.

19d ago First seen · 31 lines scan A 3a49da388ef2

Subscribe to this mod's changes

friction is a plugin published in the GitHub repository bendrucker/claude (18 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 2026-10-22.

Analytics and metrics Claude Code Productivity claude-code-plugin

friction next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
frictionbendrucker/claude	Plugin	18	today	MIT	A	—	Claude Code
ponytailDietrichGebert/ponytail	Plugin	188k	11d ago	MIT	A	—	Gemini CLI
i-have-adhdayghri/i-have-adhd	Plugin	61k	21d ago	MIT	A	—	Claude Code
dev-skillsshinpr/claude-code-workflows	Plugin	713	4d ago	MIT	A	—	Claude Code
cloudflare-browser-renderingsecondsky/claude-skills	Plugin	248	9d ago	MIT	A	—	Claude Code
handbookNikiforovAll/claude-code-rules	Plugin	142	7d ago	Apache-2.0	A	—	Claude Code
hermitd-feedgtapps/hermitd	Plugin	84	today	MIT	A	—	Claude Code