agentmods.dev

MCP_Market_Distribution: Command for Claude Code

.claude/commands/prep-mcp.md

prep-mcp is a command for Claude Code from g-digital-by-Garrigues/MCP_Market_Distribution. It costs 21 tokens per session (1,138 once invoked), scanned A, original, MIT.

A local release command that validates an MCP source folder, generates its marketplace files, and can create a Git commit and version tag. A version tag is a Git label marking a release.

In plain words
What is it for?
Use it to prepare a named MCP for distribution, run it as a dry run, or inspect generated files before committing or tagging the release.
Why use it?
It gathers the preparation steps into one repeatable process and stops when a required check fails.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument; mentions Claude Code.

This is g-digital-by-Garrigues/MCP_Market_Distribution's own configuration. It tells Claude Code how to work on MCP_Market_Distribution 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 MCP_Market_Distribution configures →

not rated 0repo changed 3d ago A scan 21 tokens original MIT
View source ↗ g-digital-by-Garrigues/MCP_Market_Distribution
Reuse

Borrowing it

Nothing to install: this file belongs to g-digital-by-Garrigues/MCP_Market_Distribution. 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/g-digital-by-Garrigues/MCP_Market_Distribution/main/.claude/commands/prep-mcp.md
Clone the repo
git clone --depth 1 https://github.com/g-digital-by-Garrigues/MCP_Market_Distribution

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 prep-mcp

README.md
[![agentmods](https://agentmods.dev/badge/commands/g-digital-by-garrigues/mcp_market_distribution/prep-mcp/github.svg)](https://agentmods.dev/commands/g-digital-by-garrigues/mcp_market_distribution/prep-mcp)
Your own site
<a href="https://agentmods.dev/commands/g-digital-by-garrigues/mcp_market_distribution/prep-mcp"><img src="https://agentmods.dev/badge/commands/g-digital-by-garrigues/mcp_market_distribution/prep-mcp/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 prep-mcp

Your own site · 80×15
<a href="https://agentmods.dev/commands/g-digital-by-garrigues/mcp_market_distribution/prep-mcp"><img src="https://agentmods.dev/badge/commands/g-digital-by-garrigues/mcp_market_distribution/prep-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,138 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 $0.00021 $0.01138
Opus 5 $0.00010 $0.00569
Sonnet 5 $0.00004 $0.00228
Haiku 4.5 $0.00002 $0.00114

Measured 3d ago against content hash 411f484a50cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

prep-mcp 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 3d 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/prep-mcp.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prep-mcp — Local Prep Agent

You are the g-digital MCP Distribution Pipeline Prep Agent. Your job is to take an MCP source folder under pending-to-publish/<mcp-name>/ and produce every marketplace artifact + a tagged release commit, deterministically and locally (no network beyond the pinned MCP schema snapshot we already vendor).

Inputs

  • $1 (required): MCP name, e.g. ead-factory. Must match a kebab-case key under mcp-pipeline.yaml#mcps AND the folder name under pending-to-publish/.
  • --skip-commit (optional): generate artifacts without making a git commit. Useful for dry-runs.
  • --skip-tag (optional): skip the v tag creation. Useful when the engineer wants to inspect artifacts before tagging.

What you must do

  1. From the repo root, run: pnpm tsx src/prep-agent/prep-mcp.ts $1 [flags].
  2. The CLI orchestrates these steps in order — halt on the first non-zero step:
    1. Load + validate mcp-pipeline.yaml via the Story 1.2 zod schema.
    2. Story 1.3: validate the source folder (package.json, mcpName, LICENSE, .env.example, README).
    3. Resolve the next version from pending-to-publish/<mcp-name>/package.json#version (engineer-managed for v1; Story 1.4 takes over once commit-driven versioning is wired in CI).
    4. Story 1.5: generate the environmentVariables manifest from .env.example.
    5. Story 1.6: generate server.json (validated against the pinned MCP schema).
    6. Story 1.7: generate smithery.yaml (configSchema validated against JSON Schema 2020-12).
    7. Story 1.8: generate one install block per supported client.
    8. Story 1.9: assemble the published README from the source README's markers.
    9. Story 1.10: ensure package.json#files includes the bundled Claude Code skills glob.
    10. Write every artifact into pending-to-publish/<mcp-name>/ (the publishable folder).
    11. Stage + commit the changes (skipped with --skip-commit) — inside the source repo when pending-to-publish/<mcp-name>/ is its own clone (the v1.1 per-repo model), falling back to the pipeline repo for the v1.0 flat layout. Committing in the pipeline repo under v1.1 would capture only the gitlink pointer and leave every artifact uncommitted in the clone.
    12. Story 1.11: create the annotated v<semver> tag at HEAD (skipped with --skip-tag) — in the same repo as the commit above.
  3. On success, the CLI prints a JSON result with mcpName, version, artifacts, commitSha, and tagName. Summarize that in the chat for the engineer in plain prose.
  4. On failure, the CLI exits non-zero and writes a { step, cause, action } report to stderr. Surface the action line to the engineer verbatim as the next step.

Read the full file on GitHub · 48 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. 3d ago Changed 411f484a50cc
  2. 11d ago First seen · 48 lines · 21 tokens per session scan A e82e9c6cba01

Subscribe to this mod's changes

prep-mcp is a command published in the GitHub repository g-digital-by-Garrigues/MCP_Market_Distribution (0 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 1,138 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.

CommitsGit and workflowReleases
Related

Other commands, from other repositories

commit-push-pr

Commit, push, and open a PR.

anthropics/claude-plugins-official · 8 tokens

commit

Automatically generate commit message based on changes and push to current branch. Analyzes git diff to create meaningful commit following conventional commits format. Optionally creates and pushes a git tag.

dykyi-roman/awesome-claude-code · 36 tokens

commit

Smart conventional commit with security validation, branch flow enforcement, and auto-detection. Use for git commit, commit changes, save work, stage and commit.

fusengine/agents · 31 tokens

changelog-auto

Auto-generar entradas de CHANGELOG.md desde commits convencionales. Usa cuando el usuario dice "generar changelog", "update changelog", "changelog", "conventional commits", "auto changelog", "release notes", "generar release notes", "伽 changelog". Genera entradas desde conventional commits (feat, fix, docs, etc.) con…

doncheli/don-cheli-sdd · 80 tokens

flow

Universal workflow entry point. Use /flow for skill-driven GitHub development. Verbs: start, commit, pr, review, address, merge, resolve, release, status, learn, setup, explain, debug, design, brainstorm, issue.

synaptiai/synapti-marketplace · 56 tokens

changelog

Gera changelogs a partir do histórico git e valida commits convencionais. Uso: /changelog [opções].

ricneves-ai/flowgrammers-skills · 33 tokens