p7-prepare

p7-prepare is a command for Claude Code from jonase47/ccpr. It costs 0 tokens per session (1,365 once invoked), scanned A, original, MIT.

A deployment preparation checklist for a chosen environment, such as staging or production. It checks infrastructure, database changes, configuration, security, privacy requirements, and approval status before release.

In plain words
What is it for?
Use it to prepare environments, review database migrations, verify settings, and confirm that a release is ready for deployment.
Why use it?
It helps catch missing setup or overlooked risks before software is deployed. It also prevents deployment from starting before the required approval gate is complete.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: reads .claude/ paths.

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/jonase47/ccpr/p7-prepare
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr

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 p7-prepare

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonase47/ccpr/p7-prepare.svg)](https://agentmods.dev/commands/jonase47/ccpr/p7-prepare)
Your own site
<a href="https://agentmods.dev/commands/jonase47/ccpr/p7-prepare"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p7-prepare.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 1,365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.01365
Opus 5 $0.00000 $0.00682
Sonnet 5 $0.00000 $0.00273
Haiku 4.5 $0.00000 $0.00136

Measured 2d ago against content hash 86ee1faeaddb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

p7-prepare 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 2d 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.

commands/p7-prepare.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/p7-prepare – Deployment Preparation & Pre-Launch Checklist

Prepares the deployment: checks all environments, prepares database migrations, verifies configurations, and ensures nothing has been overlooked. Only after this checklist is complete will /p7-deploy be executed.

Argument: $ARGUMENTS = [Environment, e.g. "staging", "production"]

If provided: Prepare the deployment for the specified environment. If not provided: Ask for the target environment. Default order is staging first, then production – confirm or adjust accordingly.

Execution

1. Read Context

Read the following files (if available):

  • INFRASTRUCTURE.md (Hosting, Environments, Rollback strategy)
  • GATE_P6.md (Approval status – deployment only after Gate 6 has passed)
  • SECURITY.md (Security requirements for production deployment)
  • DSGVO_INITIAL_ASSESSMENT.md (DSGVO (GDPR) obligations before go-live)
  • DATA_MODEL.md (Identify database migrations)

2. Verify Gate 6 Approval

Before preparation starts: Does GATE_P6.md exist with a green or yellow approval from both reviewers? If not: Stop and point out that Gate 6 must be completed first.

3. Delegation to DevOps Agent (Lead)

Delegate deployment preparation to the devops agent:

Prepare the deployment for the following environment: $ARGUMENTS Context from INFRASTRUCTURE.md: [Apply hosting, environment configurations, CI/CD pipeline]

A. Environment Check

  • Are all required environment variables set in the target environment?
  • Are configurations correct (CORS origins, Allowed Hosts, API URLs) for the target environment?
  • Are all external services (email, payment, monitoring) configured for the target environment?
  • Are secrets correctly stored (database passwords, API keys, certificates)?

B. Database Migrations

  • Which migrations need to be executed for this deployment?
  • Have all migrations been successfully tested on the staging environment?
  • Are there destructive migrations (DROP COLUMN, DELETE)? If so: backup beforehand?
  • Is a rollback of the migrations possible if needed?

C. Deployment Artifacts

  • Is the release branch clearly identified and tagged (e.g. v1.0.0)?
  • Are all CI checks passing on the release tag?
  • Are Docker images built and available in the container registry?

D. Rollback Plan

  • What is the rollback procedure if the deployment fails?
  • How long does a rollback take?
  • Who is responsible for the rollback decision?
  • Are the database state and application code consistent during a rollback?

E. Downtime Planning

  • Is a maintenance page/maintenance mode prepared for the deployment?
  • Is there a zero-downtime deployment (Blue/Green, Rolling Update)?
  • If downtime is unavoidable: what is the best time window?

F. Pre-Launch Checklist Create a concrete, actionable checklist for the upcoming deployment. Each item should be checkable as ✅/❌.

Read the full file on GitHub · 120 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. 2d ago First seen · 120 lines · 0 tokens per session scan A 86ee1faeaddb

Subscribe to this mod's changes

p7-prepare is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,365 tokens. 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 2026-09-03.