add-tool

add-tool is a command for Claude Code from opensesh/DESIGN-OPS. It costs 0 tokens per session (2,278 once invoked), scanned C, original, Apache-2.0.

A guided command for connecting a new tool to DESIGN-OPS. It evaluates available connection methods, such as MCP or an API, before updating the configuration.

In plain words
What is it for?
Use it to add a named tool, choose its DESIGN-OPS category, assess whether it can connect, and record it in the right configuration section.
Why use it?
It gives the setup a consistent path instead of requiring you to decide manually how a tool should connect and where it belongs.

Command for Claude Code

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

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

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.

agentmods
npx agentmods add commands/opensesh/design-ops/add-tool
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 add-tool

README.md
[![agentmods](https://agentmods.dev/badge/commands/opensesh/design-ops/add-tool.svg)](https://agentmods.dev/commands/opensesh/design-ops/add-tool)
Your own site
<a href="https://agentmods.dev/commands/opensesh/design-ops/add-tool"><img src="https://agentmods.dev/badge/commands/opensesh/design-ops/add-tool.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,278 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
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 $0.02278
Opus 5 $0.00000 $0.01139
Sonnet 5 $0.00000 $0.00456
Haiku 4.5 $0.00000 $0.00228

Measured 6d ago against content hash abd548f3f3d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

add-tool scanned grade C with 2 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 6d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

2. Try running with sudo: `sudo claude mcp add ...`

Reads agent configuration directoriesmediumAgent snooping

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

- Search `~/.claude/settings.json` for existing MCP
commands/add-tool.md · 428 lines

How it starts

The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/design-ops:add-tool

Guided setup for adding a new tool to DESIGN-OPS. Uses the evaluation cascade to determine the best connection method.

Trigger

User runs /design-ops:add-tool or /design-ops:add-tool {toolname} to connect a new tool.


Workflow Overview

User wants to add a tool
        │
        ▼
┌───────────────────────┐
│ 1. Identify the tool  │ ← Which tool? Which pillar?
└───────────────────────┘
        │
        ▼
┌───────────────────────┐
│ 2. Evaluate the tool  │ ← Check MCP → Check API → Assess viability
└───────────────────────┘
        │
        ▼
┌───────────────────────┐
│ 3. Guide connection   │ ← Based on evaluation results
└───────────────────────┘
        │
        ▼
┌───────────────────────┐
│ 4. Update config      │ ← Add to appropriate pillar
└───────────────────────┘

Step 1: Identify the Tool

If tool specified in command

/design-ops:add-tool substack

Parse the tool name and proceed to evaluation.

If no tool specified

Present options organized by pillar:

## Add a New Tool

What would you like to connect?

**Operations (coordination, scheduling, tasks):**
1. Notion — Tasks, docs, wikis
2. Google Workspace — Calendar, email, docs
3. Linear — Issue tracking
4. Asana — Project management
5. Slack — Communication

**Design (code, creative work):**
6. GitHub — Repos, PRs, issues
7. GitLab — Repos, merge requests
8. Figma — Design files
9. Bitbucket — Repos, PRs

**Analytics (metrics, insights):**
10. Google Analytics (GA4) — Web traffic
11. Dub.co — Link analytics
12. Plausible — Privacy-focused analytics
13. Substack — Newsletter metrics
14. Bitly — Link tracking

**Other:**
15. Custom tool — I'll specify the name

Which one? (enter number or name)

Step 2: Evaluate the Tool

Use the tool-evaluator skill to assess the tool:

Evaluating {tool_name}...

Evaluation Cascade

  1. Check for MCP
    • Search ~/.claude/settings.json for existing MCP
    • Check references/tool-registry.md for known MCPs
    • Determine if MCP supports reporting data we need

Read the full file on GitHub · 428 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. 6d ago First seen · 428 lines · 0 tokens per session scan C abd548f3f3d0

Subscribe to this mod's changes

add-tool is a command 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 2,278 tokens. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.