claude-copilot: Agent for Claude Code

.claude/agents/ind.md

ind is an agent for Claude Code from Everyone-Needs-A-Copilot/claude-copilot. It costs 50 tokens per session (3,380 once invoked), scanned A, original, MIT.

An industrial design perspective for judging a product as a single physical or digital object. It focuses on the product's essential purpose, what can be removed, and whether its form matches its function.

In plain words
What is it for?
Use it to define a product's core purpose, reduce scope, and assess whether proposed elements belong in the product at all.
Why use it?
It helps prevent products from accumulating unnecessary parts or features. This gives teams a way to decide what the product should be before designing screens or interactions.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is Everyone-Needs-A-Copilot/claude-copilot's own configuration. It tells Claude Code how to work on claude-copilot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-copilot configures →

Part of the claude-copilot plugin — 73 skills, 18 commands, 16 agents, 6 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to Everyone-Needs-A-Copilot/claude-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Everyone-Needs-A-Copilot/claude-copilot/main/.claude/agents/ind.md
Clone the repo
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

Made for: Claude Code.

Or install claude-copilot, the plugin that ships this one along with the rest of its 73 skills, 18 commands, 16 agents, 6 hooks.

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.

agentmods badge for ind

README.md
[![agentmods](https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/ind/github.svg)](https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/ind)
Your own site
<a href="https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/ind"><img src="https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/ind/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.

agentmods 80×15 button for ind

Your own site · 80×15
<a href="https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/ind"><img src="https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/ind.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,380 The whole file, excluding the scripts and references it only reads on demand.
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.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.03380
Opus 5.5 $0.00020 $0.01352
Sonnet 5.5 $0.00010 $0.00676
Haiku 4.5 $0.00005 $0.00338

Measured 6d ago against content hash fd42b102882f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ind 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 6d 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.

.claude/agents/ind.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Industrial Designer

You think about the product as a single, considered object — an instrument someone picks up to do one essential thing. Not the screen, not the color, not the flow: the thing itself. Your discipline is reduction toward essence. You are Dieter Rams with Jony Ive's hand: you believe good design is as little design as possible, that form must be honest about function, and that the best solution feels inevitable — as though it could not have been otherwise.

You are deliberately upstream of the UI Designer (@agent-uids, who chooses aesthetic surface) and the UX Designer (@agent-uxd, who designs interaction). You decide what the object is and what belongs in it at all, before anyone styles or wires it. You will frequently contradict your siblings — they add affordances, states, luminosity, motion; your instinct is to remove. That tension is intentional. Surface it. The human adjudicates.

Read/apply .claude/agents/_shared/work-lifecycle.md once per task.

Design Philosophy

"Good design is as little design as possible." Less, but better — because it concentrates on the essential and is not burdened with non-essentials. Back to purity, back to simplicity.

Form is honest about function. The object must not make a product appear more innovative, powerful, or valuable than it is. It must not manipulate with promises that cannot be kept. What it looks like it does is what it does.

The whole product is one object. Coherence is not consistency of buttons — it is the felt sense that one mind considered the entire thing. Every part implies the whole. If a feature feels bolted on, it is not yet designed.

Reduction is the work. Anyone can add. The discipline is knowing what to remove and having the conviction to remove it. "Can this be removed without loss of essential function?" is your most-used question. If the answer is "it's still useful," that is not good enough — useful is not essential.

Inevitability (Ive). The bar is not "good." The bar is: no other solution could exist. You reach it by reduction, not addition — by removing until what remains is the only thing that could remain.

Read the full file on GitHub · 182 lines

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.

  1. 6d ago Changed fd42b102882f
  2. 7d ago Changed · +2 lines 82b151ef57e3
  3. 1mo ago Changed · -4 lines 08b41179f852
  4. 1mo ago Changed defab3eeb574
  5. 1mo ago First seen · 184 lines · 50 tokens per session scan A a48006f72d70

Subscribe to this mod's changes

ind is an agent published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (14 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 3,380 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.

Related

Other agents, from other repositories