agentmods.dev

designing-tools-and-mcp

designing-tools-and-mcp is a skill for Claude Code from atretyak1985/swarmery. It costs 127 tokens per session (1,253 once invoked), scanned A, original, Apache-2.0.

A skill for creating or reviewing Claude’s tool definitions and MCP server configuration. It covers tool names, descriptions, input formats, errors, and choosing between similar tools.

In plain words
What is it for?
Use it to design or troubleshoot Claude tools, MCP servers, schemas, tool selection, and built-in tools such as search, file listing, reading, and editing.
Why use it?
Clear tool definitions reduce wrong tool choices, confused retries, and invalid inputs.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the claude-eng-pack plugin — 5 skills shipped together

not rated 7repo changed 2mo ago A scan 127 tokens original Apache-2.0

Good fit Use it to design or troubleshoot Claude tools, MCP servers, schemas, tool selection, and built-in tools such as search, file listing, reading, and editing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/atretyak1985/swarmery/designing-tools-and-mcp
View source ↗ atretyak1985/swarmery atretyak1985.github.io
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 atretyak1985/swarmery --skill designing-tools-and-mcp
Clone the repo
git clone --depth 1 https://github.com/atretyak1985/swarmery

Made for: Claude Code.

Or install claude-eng-pack, the plugin that ships this one along with the rest of its 5 skills.

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 designing-tools-and-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/atretyak1985/swarmery/designing-tools-and-mcp/github.svg)](https://agentmods.dev/skills/atretyak1985/swarmery/designing-tools-and-mcp)
Your own site
<a href="https://agentmods.dev/skills/atretyak1985/swarmery/designing-tools-and-mcp"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/designing-tools-and-mcp/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 designing-tools-and-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/atretyak1985/swarmery/designing-tools-and-mcp"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/designing-tools-and-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,253 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 $0.00127 $0.01253
Opus 5.5 $0.00051 $0.00501
Sonnet 5.5 $0.00025 $0.00251
Haiku 4.5 $0.00013 $0.00125

Measured 2mo ago against content hash 5d09f09f2a84, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

designing-tools-and-mcp 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 2mo 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/claude-eng-pack/skills/designing-tools-and-mcp/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Designing Tools and MCP

Overview

Best-practice reference for the tool layer: how tools are named, described, split, scoped, and how their errors are structured so the model can act on them. Each reference module states the correct pattern, the named anti-patterns, and ends with an Audit Checklist of verifiable conditions.

When to use

  • Writing or reviewing tool schemas, descriptions, or an MCP server
  • Debugging: misrouted tool calls, retry loops on permanent errors, "no results" handled as failure, tool overload
  • Deciding: one tool or several, tool_choice mode, build vs use an existing MCP server, which built-in tool fits

Not for the agent loop itself (use auditing-agent-architecture) or output schemas for extraction (use engineering-prompts-and-output).

Quick reference

Module Read when the question is about
references/2-1-tool-interface-design.md Descriptions that route correctly, splitting overloaded tools, naming
references/2-2-structured-error-responses.md Error categories, isRetryable, access failure vs valid empty result
references/2-3-tool-distribution-and-tool-choice.md Tool overload, tool_choice config, role-scoped tool sets
references/2-4-mcp-server-integration.md MCP scoping hierarchy, env-var expansion, resources, build-vs-use
references/2-5-built-in-tools.md Grep vs Glob, Read/Write/Edit, incremental codebase understanding

How to audit

  1. Match the tool surface under review to modules in the table; read those files.
  2. Run each module's Audit Checklist item by item against the actual definitions/config.
  3. Report every unchecked item as a finding with file:line evidence and the module's recommended fix.

For a fast full-domain sweep, checklists.md aggregates all five checklists.

How tool errors should propagate between agents: managing-context-reliability (5-3). Forcing structured output via tools: engineering-prompts-and-output (4-3).

How to use

Read the full file on GitHub · 98 lines

Files

What ships with it

6 files 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. 2mo ago Changed · +39 tokens per session 5d09f09f2a84
  2. 2mo ago First seen · 98 lines · 88 tokens per session scan A bbe4ca8b9bc9

Subscribe to this mod's changes

designing-tools-and-mcp is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed 2d ago), licensed Apache-2.0. It adds 127 tokens to every session and 1,253 once invoked, about $0.0005 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 2026-08-31.

Building agentsClaude Codeagentsai-agentsclaude-code-pluginsplugin-marketplace
Related

designing-tools-and-mcp compared with skills from other repositories

designing-tools-and-mcp next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
designing-tools-and-mcpatretyak1985/swarmerySkill72d agoApache-2.0A127Claude Code
dependency-versionsnetopsengineer/axiomSkill5yesterdayMITA216Claude Code
finishfakoli/fakoli-pluginsSkill41mo agoMITA18Claude Code
gws-quick-reffakoli/fakoli-pluginsSkill41mo agoMITA29Claude Code
excalidrawfakoli/fakoli-pluginsSkill41mo agoMITA28Claude Code, Codex
gws-events-subscribefakoli/fakoli-pluginsSkill41mo agoMITA21Claude Code
gws-scriptfakoli/fakoli-pluginsSkill41mo agoMITA21Claude Code