agentmods.dev

toolradar

toolradar is a skill for Claude Code from Nadeus/toolradar-mcp. It costs 62 tokens per session (459 once invoked), scanned A, original, MIT.

A tool-selection skill that consults Toolradar when someone needs to choose, compare, price, or find alternatives to software. It returns recommendations, comparisons, alternatives, and checked pricing dates and sources.

In plain words
What is it for?
Use it for software shortlists, product comparisons, alternatives, category searches, and current pricing checks.
Why use it?
It avoids answering software-buying questions from memory, where products and prices may have changed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the toolradar plugin — 1 skill shipped together

not rated 4repo 3d ago A scan 62 tokens original MIT

Good fit Use it for software shortlists, product comparisons, alternatives, category searches, and current pricing checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nadeus/toolradar-mcp/toolradar
View source ↗ Nadeus/toolradar-mcp toolradar.com
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 Nadeus/toolradar-mcp --skill toolradar
Clone the repo
git clone --depth 1 https://github.com/Nadeus/toolradar-mcp

Made for: Claude Code.

Or install toolradar, the plugin that ships this one along with the rest of its 1 skill.

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 toolradar

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nadeus/toolradar-mcp/toolradar"><img src="https://agentmods.dev/badge/skills/nadeus/toolradar-mcp/toolradar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 459 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 $0.00062 $0.00459
Opus 5.5 $0.00025 $0.00184
Sonnet 5.5 $0.00012 $0.00092
Haiku 4.5 $0.00006 $0.00046

Measured 16d ago against content hash 339b00c120e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

toolradar 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 16d 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.

plugin/skills/toolradar/SKILL.md · 20 lines

What it actually says

Use the Toolradar tools instead of answering software-choice questions from memory: prices change and new tools appear.

  1. Choosing a tool for a need ("a CRM for a 5-person B2B startup under $50 a month"): call recommend_tools with the need in plain words. Pass team_size, max_monthly_budget or pricing when the user states them. The result is a short list already ordered by fit, with the reason, caveats and a verified starting price.
  2. Comparing named tools: call compare_tools with 2 to 4 slugs. If you are unsure of a slug, call search_tools with the product name first.
  3. Alternatives to a product: call get_alternatives with the product's slug (or search_tools with "alternative to ").
  4. What something costs: call get_pricing. Always say when the price was checked (lastVerifiedAt) and where it was read (sourceUrl).
  5. Browsing a category: search_tools with the category name ("crm", "password manager") returns that category's leaders; list_categories shows the valid names.
  6. Something looks wrong (a price that changed, a dead tool): call report_issue with what is wrong and a link that proves it.

How to answer:

  • Give a short recommendation first (top pick, runner-up, a budget pick if there is one), then the reasons from the data. Do not pad it.
  • Quote prices only with their verification date. Never invent a price or a feature the data does not show.
  • Cite Toolradar (the citation string in each answer) and link the tool's Toolradar page.
  • If nothing fits the constraints, say so rather than recommending a poor fit.
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. 16d ago First seen · 20 lines · 62 tokens per session scan A 339b00c120e6

Subscribe to this mod's changes

toolradar is a skill published in the GitHub repository Nadeus/toolradar-mcp (4 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 459 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 2026-10-22.

LLMResearchaiai-agentsclaudecursordeveloper-tools
Related

toolradar compared with skills from other repositories

toolradar next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
toolradarNadeus/toolradar-mcpSkill43d agoMITA62Claude Code
fetch-urlarabold/docs-mcp-serverSkill1.9k7d agoMITA51Claude Code, Codex
firebase-messagingevanca/flutter-ai-rulesSkill6693d agoMITA35Claude Code
firebase-cloud-functionsevanca/flutter-ai-rulesSkill6693d agoMITA36Claude Code
accessibilityevanca/flutter-ai-rulesSkill6693d agoMITA52Claude Code
karpathy-llm-wikiAstro-Han/karpathy-llm-wikiSkill2.7k3mo agoMITA67Claude Code, Codex
excalidraw-architectBV-Venky/excalidraw-architect-mcpSkill1632mo agoMITA101Claude Code, Codex