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.
npx skills add opensesh/DESIGN-OPS --skill tool-evaluatorgit clone --depth 1 https://github.com/opensesh/DESIGN-OPSWrote 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.
[](https://agentmods.dev/skills/opensesh/design-ops/tool-evaluator)<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.
<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>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.
| Model | Per session | Once 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 |
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' 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:
- Checks if the tool is already installed and connected
- Invokes the
mcp-discoveryskill for unknown tools - 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"]
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.
- 9d ago First seen · 402 lines · 0 tokens per session scan B e3231ade7681
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.
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…
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…
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…
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…
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…
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…