agent-design

agent-design is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 52 tokens per session (1,287 once invoked), scanned A, original, MIT.

Guidance for designing the tools and actions available to AI agents. It explains how to shape tool interfaces around what an agent can understand and use effectively.

In plain words
What is it for?
Use it when building agent harnesses, defining tool interfaces, designing user-input questions, or improving how agents interact with tools.
Why use it?
Poorly designed tools can confuse agents or make them follow unnecessary workarounds. These guidelines help reduce unclear tool calls and restrictive interfaces.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; names the TodoWrite tool; mentions Claude Code.

Good fit Use it when building agent harnesses, defining tool interfaces, designing user-input questions, or improving how agents interact with tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-design-christophe1997-agent-extentions
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.

Any agent
npx skills add majiayu000/claude-skill-registry --skill agent-design-christophe1997-agent-extentions
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

Made for: Claude Code, Codex.

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 agent-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-design-christophe1997-agent-extentions/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-design-christophe1997-agent-extentions)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-design-christophe1997-agent-extentions"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-design-christophe1997-agent-extentions/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 agent-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-design-christophe1997-agent-extentions"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-design-christophe1997-agent-extentions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,287 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00052 $0.01287
Opus 5 $0.00026 $0.00643
Sonnet 5 $0.00010 $0.00257
Haiku 4.5 $0.00005 $0.00129

Measured 9d ago against content hash 453de99eeec4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

agent-design 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 9d 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.

skills/agent/agent-design-christophe1997-agent-extentions/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Design Guidelines

Overview

Designing tools for AI agents is as much art as science. The key principle: give agents tools shaped to their own abilities — which you discover by paying attention to their outputs.

The Mental Model

Imagine being given a difficult math problem. What tools would you want?

Tool Limitation
Paper only Limited by manual calculations
Calculator Better, but requires knowledge to operate
Computer Most powerful, but requires coding skills

The right tool depends on your own abilities. Same for agents — design tools that match what the model can actually do well.

Core Principles

1. Claude Must "Like" Calling the Tool

Even the best designed tool doesn't work if Claude doesn't understand how to call it.

  • Test if the model naturally uses the tool
  • Read outputs to see if it's confused
  • Iterate on the interface until it "clicks"

2. Tools That Were Necessary Can Become Constraints

As models improve:

  • Old workarounds become unnecessary
  • Previous "helps" become limitations
  • Constantly revisit assumptions

Example: TodoWrite reminders helped older models but made newer ones think they couldn't modify the list.

3. Progressive Disclosure Over Context Bloat

Instead of stuffing everything in the system prompt:

  • Give agents tools to discover context themselves
  • Let them search, read, and explore recursively
  • Skills can reference other files for nested discovery

4. High Bar for New Tools

More tools = more options to think about = cognitive overhead.

  • Claude Code has ~20 tools
  • Consider: can this be a subagent? A skill? Progressive disclosure?
  • Only add tools when truly necessary

Design Patterns

Pattern: Structured Elicitation (AskUserQuestion)

Problem: Claude asking questions in plain text was slow and unstructured.

Failed Attempts:

  1. Adding questions to another tool's output → confused the model
  2. Modified markdown format → unreliable output

Read the full file on GitHub · 197 lines

Files

What ships with it

1 file beside SKILL.md 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.

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. 9d ago First seen · 197 lines · 52 tokens per session scan A 453de99eeec4

Subscribe to this mod's changes

agent-design is a skill published in the GitHub repository majiayu000/claude-skill-registry (606 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,287 once invoked, about $0.0003 per session on Opus 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 2026-09-03.