tool-evaluator

tool-evaluator is a skill for Claude Code from opensesh/DESIGN-OPS. It costs 0 tokens per session (2,548 once invoked), scanned B, original, Apache-2.0.

A helper skill used during design-ops setup to check whether selected tools are connected and what they can do. MCP is a standard connection that lets an agent use an external tool or service.

In plain words
What is it for?
Use it during setup to evaluate tools such as Notion, Figma, or Substack and produce a capability and connection-status summary.
Why use it?
It shows whether a tool is ready to use and distinguishes a connected tool from one that is merely available, API-only, unavailable, or skipped.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions subagents.

Part of the design-ops plugin — 5 skills, 13 commands shipped together

Good fit Use it during setup to evaluate tools such as Notion, Figma, or Substack and produce a capability and connection-status summary.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/opensesh/design-ops/tool-evaluator
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 opensesh/DESIGN-OPS --skill tool-evaluator
Clone the repo
git clone --depth 1 https://github.com/opensesh/DESIGN-OPS

Made for: Claude Code.

Or install design-ops, the plugin that ships this one along with the rest of its 5 skills, 13 commands.

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 tool-evaluator

README.md
[![agentmods](https://agentmods.dev/badge/skills/opensesh/design-ops/tool-evaluator/github.svg)](https://agentmods.dev/skills/opensesh/design-ops/tool-evaluator)
Your own site
<a href="https://agentmods.dev/skills/opensesh/design-ops/tool-evaluator"><img src="https://agentmods.dev/badge/skills/opensesh/design-ops/tool-evaluator/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 tool-evaluator

Your own site · 80×15
<a href="https://agentmods.dev/skills/opensesh/design-ops/tool-evaluator"><img src="https://agentmods.dev/badge/skills/opensesh/design-ops/tool-evaluator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,548 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00000 $0.02548
Opus 5 $0.00000 $0.01274
Sonnet 5 $0.00000 $0.00510
Haiku 4.5 $0.00000 $0.00255

Measured 9d ago against content hash e3231ade7681, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

tool-evaluator scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/settings.json | jq '.mcpServers'
skills/tool-evaluator/SKILL.md · 402 lines

How it starts

The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool Evaluator Skill

Sub-agent skill for evaluating tools during /design-ops:setup. Coordinates MCP availability checks and API capability evaluation.

Purpose

When a user selects tools in the setup flow, this skill:

  1. Checks if the tool is already installed and connected
  2. Invokes the mcp-discovery skill for unknown tools
  3. Returns a unified result with connection type and status

Trigger

Invoked by /design-ops:setup during tool evaluation phase. Should run as a background sub-agent.


Input

tools:
  - name: "notion"
    pillar: "operations"
  - name: "figma"
    pillar: "design"
  - name: "substack"
    pillar: "analytics"

Output

Returns a capability matrix for each tool, including discovery metadata:

results:
  - tool: notion
    connection_type: mcp
    mcp_name: "notion"
    status: connected    # connected | available | api_only | unavailable | skipped

    # Discovery metadata (from mcp-discovery skill)
    mcp_source: official          # official | vendor | community | none
    mcp_package: "@notionhq/notion-mcp-server"
    mcp_confidence: high          # high | medium | low

    # Capabilities
    capabilities:
      data_types: [pages, databases, tasks, comments]
      reporting:
        daily: [recent_pages, task_counts, recent_comments]
        weekly: [page_activity, task_completion]
        monthly: [content_growth]

    setup_required: false
    warning: null

  - tool: figma
    connection_type: api
    status: api_only

    # Discovery metadata
    mcp_source: official
    mcp_package: null    # MCP exists but is code-focused
    mcp_confidence: low
    api_docs_url: "https://www.figma.com/developers/api"

    capabilities:
      data_types: [files, versions, comments, users]
      reporting:
        daily: [files_edited, active_users]
        weekly: [design_versions, comment_activity]
        monthly: [project_progress]

    setup_required: true
    setup_instructions: "Generate API token at figma.com/developers"
    note: "Official MCP is code-focused. Use API for reporting."

  - tool: gitlab
    connection_type: mcp
    status: available

    # Discovery metadata
    mcp_source: community
    mcp_package: "mcp-gitlab"
    mcp_confidence: medium

    capabilities:
      data_types: [projects, commits, merge_requests, issues, pipelines]
      reporting:
        daily: [recent_commits, open_mrs]
        weekly: [contributions, mr_activity]

    setup_required: true
    setup_instructions: "claude mcp add gitlab -- npx -y mcp-gitlab"
    warning: "Community package - not officially supported"
    warning_code: community_package

  - tool: instagram
    connection_type: unavailable
    status: unavailable

    mcp_source: none
    mcp_confidence: none

    reason: "API limited to business accounts with complex approval process"
    alternatives: ["Buffer", "Later", "Sprout Social"]

Read the full file on GitHub · 402 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. 9d ago First seen · 402 lines · 0 tokens per session scan B e3231ade7681

Subscribe to this mod's changes

tool-evaluator is a skill published in the GitHub repository opensesh/DESIGN-OPS (23 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,548 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

system-pitch

Write a design system investment pitch with a business case and ROI framing. Trigger when someone says: pitch the design system, make the case for the system, sell this to leadership, justify the investment, business case for design systems, why should we invest in a design system, or anything about building an…

murphytrueman/design-system-ops · 72 tokens

ai-component-description

Generate AI-optimised text descriptions for components, formatted for Figma's MCP server and LLM consumption. This produces prose descriptions in a six-section format (purpose, props, anti-patterns, composition, accessibility, examples), NOT JSON schemas or structured data files. Trigger when someone says: write…

murphytrueman/design-system-ops · 132 tokens

stakeholder-brief

Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…

murphytrueman/design-system-ops · 73 tokens

token-audit

Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…

murphytrueman/design-system-ops · 93 tokens

accessibility-per-component

Run an accessibility audit on a specific design system component. Trigger when someone says: accessibility check, a11y audit, WCAG compliance, is this accessible, check accessibility, does this meet WCAG, screen reader support, keyboard navigation check, or anything about auditing the accessibility of a specific…

murphytrueman/design-system-ops · 65 tokens

codemod-generator

Generate codemods (automated code transformation scripts) for design system migrations — token renames, component API changes, prop deprecations, and import path updates. Produces ready-to-run jscodeshift or custom AST transform scripts that safely apply changes across consuming codebases. Trigger when someone says…

murphytrueman/design-system-ops · 162 tokens