agent-tool-design

agent-tool-design is a skill for Claude Code, Codex from IgorWarzocha/howaboua-pi-stuff. It costs 19 tokens per session (829 once invoked), scanned A, original, MIT.

Design guidance for tools that a coding agent can call. It focuses on making tool names, inputs, and choices clear to the model using them.

In plain words
What is it for?
Use it when creating, reviewing, or refining agent tools, especially their names, arguments, defaults, descriptions, and decision-boundary tests.
Why use it?
It reduces incorrect tool selection and argument choices by treating the tool contract as part of the agent interaction.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when creating, reviewing, or refining agent tools, especially their names, arguments, defaults, descriptions, and decision-boundary tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/igorwarzocha/howaboua-pi-stuff/agent-tool-design
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 IgorWarzocha/howaboua-pi-stuff --skill agent-tool-design
Clone the repo
git clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuff

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-tool-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/agent-tool-design/github.svg)](https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/agent-tool-design)
Your own site
<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/agent-tool-design"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/agent-tool-design/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-tool-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/agent-tool-design"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/agent-tool-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 829 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 $0.00019 $0.00829
Opus 5 $0.00010 $0.00415
Sonnet 5 $0.00004 $0.00166
Haiku 4.5 $0.00002 $0.00083

Measured 9d ago against content hash dac0fd58bb5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-tool-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.

packages/pi-skill-harness-and-agent-engineering/skills/agent-tool-design/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

For a Pi tool, also read references/pi.md.

Start from what the agent knows

  • Prefer canonical tool names and argument shapes already present in the target model's training.
  • Treat a familiar tool schema as a runtime binding, not a tutorial. State only this implementation's meaningful deviations.
  • Give an unfamiliar capability an obvious action name and familiar inputs. The agent should predict the call from the name and schema.
  • When unsure, present the bare contract to the target model first. Add only the fact it could not infer correctly.

Fix model choices at the model boundary

  • When the implementation supports the right behaviour but the model selects the wrong action or argument, treat it as a model-facing contract failure first.
  • Fix the name, default, argument description, or prompt guidance before adding runtime policy, heuristics, or extra state.
  • Describe choices in terms of user intent, not only mechanics. “False returns immediately” explains execution. “Use false only while continuing other work” changes the model's decision.
  • Test paired natural requests that differ only at the decision boundary. Confirm the model chooses correctly before changing implementation.

Keep the decision surface small

  • Give one tool one coherent job.
  • Expose only decisions the caller must make. Keep providers, models, prompts, commands, internal modes, formatting, and policy inside the implementation unless the agent genuinely chooses them.
  • Require only the minimum valid input. Add an optional field only when omission has a useful deterministic meaning.
  • Prefer conventional names such as cmd, path, query, cwd, and message. Use a small enum when the choice is genuinely closed.
  • If a field needs a paragraph to make sense, remove it, rename it, or reconsider the tool boundary.

Let the schema speak

  • Do not narrate types, requiredness, optionality, enums, defaults, or limits already encoded by the schema.
  • Omit a field description when its name is sufficient.
  • Write necessary descriptions as compact payload fragments: Cwd, Wait ms, Recent days, Truncate.
  • Omit cosmetic terminal full stops, backticks, Markdown, examples, and grammatical padding. Preserve punctuation and formatting only when they carry literal syntax or prevent ambiguity.
  • Keep safe compatibility aliases inside argument preparation rather than advertising them in the schema.

Read the full file on GitHub · 72 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 · 72 lines · 19 tokens per session scan A dac0fd58bb5f

Subscribe to this mod's changes

agent-tool-design is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (358 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 829 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens