quality-screener-mcp-server: Command for Claude Code

.claude/commands/release.md

release is a command for Claude Code from quality-screener/quality-screener-mcp-server. It costs 20 tokens per session (1,156 once invoked), scanned A, original, MIT.

A release procedure for increasing a software version, creating a matching Git tag, and publishing a GitHub release.

In plain words
What is it for?
Use it when releasing qscreener-mcp from the main branch, including updating version files, committing changes, tagging, and publishing.
Why use it?
It prevents version numbers from getting out of sync and helps ensure releases happen in the required order.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

This is quality-screener/quality-screener-mcp-server's own configuration. It tells Claude Code how to work on quality-screener-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything quality-screener-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to quality-screener/quality-screener-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/quality-screener/quality-screener-mcp-server/main/.claude/commands/release.md
Clone the repo
git clone --depth 1 https://github.com/quality-screener/quality-screener-mcp-server

Made for: Claude Code.

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 release

README.md
[![agentmods](https://agentmods.dev/badge/commands/quality-screener/quality-screener-mcp-server/release/github.svg)](https://agentmods.dev/commands/quality-screener/quality-screener-mcp-server/release)
Your own site
<a href="https://agentmods.dev/commands/quality-screener/quality-screener-mcp-server/release"><img src="https://agentmods.dev/badge/commands/quality-screener/quality-screener-mcp-server/release/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 release

Your own site · 80×15
<a href="https://agentmods.dev/commands/quality-screener/quality-screener-mcp-server/release"><img src="https://agentmods.dev/badge/commands/quality-screener/quality-screener-mcp-server/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,156 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 $0.00020 $0.01156
Opus 5 $0.00010 $0.00578
Sonnet 5 $0.00004 $0.00231
Haiku 4.5 $0.00002 $0.00116

Measured 5d ago against content hash d58f299b557b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

release 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 5d 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.

.claude/commands/release.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cut a new release for qscreener-mcp. The bump type is $1 (default to patch if empty).

Critical rules

  • pyproject.toml and server.json versions MUST stay in sync with each other and with the git tag. The package exposes __version__ via importlib.metadata (see qscreener_mcp/__init__.py), and it is sent to the backend as CLIENT_ID = f"mcp/{__version__}" — a stale pyproject.toml version silently corrupts usage analytics.
  • Git tags use a v prefix (e.g. v0.2.0); the version fields in pyproject.toml and server.json do NOT (e.g. 0.2.0).
  • Releases are cut directly on main — this repo has no develop branch and main is not protected. Do not open a release PR.
  • Never push or tag until the version edits are committed.
  • The agent never pushes to main. Commit and tag locally, then stop and hand off — the user runs the actual git push themselves. This mirrors the quality-screener release process, where the agent opens the release PR but leaves merging (and thus the push to main) to the user.

Steps

  1. Sync main. (Do this FIRST, before any edits.)

    • git fetch origin --tags
    • git switch main && git pull --ff-only origin main
    • Confirm the working tree is clean (git status --porcelain returns nothing). Abort and tell the user if it is not.
  2. Determine the new version.

    • Run git tag --sort=-v:refname | head -5 to find the latest tag.
    • If tags exist: parse the latest semver tag (strip the v prefix) and bump according to $1:
      • patch (default) → X.Y.(Z+1)
      • minorX.(Y+1).0
      • major(X+1).0.0
    • If no tags exist (first release): do not bump. Use the version already in pyproject.toml as-is, and say so in the final report.
    • Call the new version NEW (no v) and the tag vNEW.
    • Sanity check that vNEW does not already exist: git rev-parse -q --verify refs/tags/vNEW must fail.
  3. Update the version manifests to NEW:

    • Edit version in pyproject.toml ([project] section).
    • Edit version in server.json (top level).
    • Confirm both now read exactly NEW: grep -n '"\?version"\? *[:=]' pyproject.toml server.json.
    • Skip this step if the versions already equal NEW (first-release case).

Read the full file on GitHub · 76 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. 5d ago Changed · -1 lines d58f299b557b
  2. 10d ago First seen · 77 lines · 20 tokens per session scan A 74fcfa6a26b3

Subscribe to this mod's changes

release is a command published in the GitHub repository quality-screener/quality-screener-mcp-server (0 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 1,156 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.