What is qualimetry-setup?

A setup command for connecting Claude Code to a Qualimetry MCP server. It asks for the server address and access token, then registers the connection for the user account.

Setting up or updating Qualimetry on a machine and checking that Claude Code can find the server.

It avoids manually editing the MCP configuration and checks that the server address uses the expected path. It also warns that pasted tokens remain visible in the chat.

qualimetry-setup — Command for Claude Code by Qualimetry

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.

Clone the repo

git clone --depth 1 https://github.com/Qualimetry/claude-code-qualimetry-ai-app

Made for: Claude Code.

Or install qualimetry-ai-app, the plugin that ships this one along with the rest of its 5 skills, 6 commands, 1 agent, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/qualimetry/claude-code-qualimetry-ai-app/qualimetry-setup/github.svg)](https://agentmods.dev/commands/qualimetry/claude-code-qualimetry-ai-app/qualimetry-setup)

Your own site

<a href="https://agentmods.dev/commands/qualimetry/claude-code-qualimetry-ai-app/qualimetry-setup"><img src="https://agentmods.dev/badge/commands/qualimetry/claude-code-qualimetry-ai-app/qualimetry-setup/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/qualimetry/claude-code-qualimetry-ai-app/qualimetry-setup"><img src="https://agentmods.dev/badge/commands/qualimetry/claude-code-qualimetry-ai-app/qualimetry-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 664 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.

Model	Per session	Once invoked
Fable 5.1	$0.00017	$0.00664
Opus 5	$0.00009	$0.00332
Sonnet 5	$0.00003	$0.00133
Haiku 4.5	$0.00002	$0.00066

Measured 9d ago against content hash 2c1f3290aedb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

qualimetry-setup 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 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.

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/qualimetry-ai-app/commands/qualimetry-setup.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qualimetry: Setup

Walk the user through configuring the Qualimetry MCP server. Follow this exact procedure:

Ask the user, in plain language: "What is your Qualimetry server URL? (default: https://myorg.qualimetry.io/mcp/)". If they reply with an empty message or "default", use https://myorg.qualimetry.io/mcp/.
Ask the user: "Paste your Qualimetry access token. The text will be visible in the chat — clear the chat afterwards if you want to keep it private.". (Claude Code does not natively hide pasted text in chat; flag this honestly so the user can choose to clear after.)
Validate the URL ends in /mcp/ (or /mcp); if not, append /mcp/ and tell the user what you adjusted.
Run exactly one of the following Bash commands to register or update the MCP server (both are idempotent — add removes and re-adds when the name already exists):
```
claude mcp remove qualimetry --scope user 2>/dev/null
claude mcp add qualimetry --scope user --transport http --url "<URL>" --header "qualimetry-access-token: <TOKEN>"
```
Substitute <URL> and <TOKEN> with the values the user provided.
Verify by running:
```
claude mcp list | grep qualimetry
```
It should show the qualimetry server connected with status ✓ Connected. If it does not, ask the user to restart Claude Code so the new MCP entry is loaded, then re-run claude mcp list.
Once connected, run a smoke check by invoking the MCP tool get_policies (no arguments). If it returns a JSON array of policies, the setup is complete. If it returns an authentication error, the token is wrong — ask the user to re-run /qualimetry-setup with the correct token.
End with the verbatim message:

✓ Qualimetry configured. You can now /compliance-check, /compliance-fix, or just open a reviewed file and Qualimetry will surface any open issues automatically.

Notes for the agent

The token must never be displayed back in any subsequent chat message. Echo only **** in any quote-back.
If claude mcp is not on PATH, fall back to ~/.claude.json direct edit: read the file, locate or create the mcpServers.qualimetry entry with {"type": "http", "url": "<URL>", "headers": {"qualimetry-access-token": "<TOKEN>"}}, write it back. Tell the user they may need to restart Claude Code.
If the user re-runs this command, treat it as a re-config: remove first, add fresh.

Read the full file on GitHub · 44 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.

9d ago First seen · 44 lines · 17 tokens per session scan A 2c1f3290aedb

Subscribe to this mod's changes

qualimetry-setup is a command published in the GitHub repository Qualimetry/claude-code-qualimetry-ai-app (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 17 tokens to every session and 664 once invoked, about $0.0001 per session on Opus 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.

Claude Code Code review ai-agent claude-code-marketplace claude-code-plugin coding-standards

review

Multi-agent code review with parallel validation.

Joncik91/ucai · 7 tokens

ship

Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…

PrabhdeepSingh/claude-plugins · 86 tokens

qualimetry-setup

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Qualimetry: Setup

Notes for the agent

What this file has done since we first saw it

Other commands, from other repositories

review

ship

code-review-teach

dead-code-scan

hidden-dependencies

dead-code-clean