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.
git clone --depth 1 https://github.com/jonase47/ccprWrote 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.
[](https://agentmods.dev/commands/jonase47/ccpr/p7-deploy)<a href="https://agentmods.dev/commands/jonase47/ccpr/p7-deploy"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p7-deploy/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.
<a href="https://agentmods.dev/commands/jonase47/ccpr/p7-deploy"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/p7-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.01378 |
| Opus 5.5 | $0.00000 | $0.00551 |
| Sonnet 5.5 | $0.00000 | $0.00276 |
| Haiku 4.5 | $0.00000 | $0.00138 |
Grade A, and why
p7-deploy 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/p7-deploy – Execute Deployment & Smoke Tests
Executes the deployment to the target environment and then verifies with smoke tests that the system is running correctly. Only when the smoke tests pass is the deployment considered successful.
Argument: $ARGUMENTS = [Environment, e.g. "staging", "production"]
If provided: Deploy to the specified environment. If not provided: Ask for the target environment. Without a clear specification, do not start the deployment – the environment is critical information.
Execution
1. Read Context and Check Prerequisites
Read the following files (if available):
- PREPARE.md (has the preparation from
/p7-preparebeen completed?) - INFRASTRUCTURE.md (deployment procedure, rollback strategy)
- GATE_P6.md (approval status)
Mandatory checks before deployment:
- Does PREPARE.md exist with a completed checklist? If not → stop, recommend
/p7-preparefirst. - Is Gate 6 approved with green or yellow? If not → stop.
2. Delegation to DevOps Agent (Lead)
Delegate the deployment to the devops agent:
Execute the deployment to the following environment: $ARGUMENTS Deployment procedure from INFRASTRUCTURE.md and PREPARE.md: [Apply procedure]
A. Execute Deployment Execute the deployment step by step and document each step:
- Activate maintenance mode (if no zero-downtime deployment)
- Execute database migrations
- Deploy new application version
- Restart services / switch traffic
- Deactivate maintenance mode Log timestamp and result for each step.
B. Smoke Tests Immediately after deployment, verify the most critical system functions:
- Is the application reachable? (HTTP 200 on the home page)
- Does authentication work? (Login successful)
- Is the database connection active? (Health endpoint or simple DB query)
- Does the most critical core workflow work? (1 E2E smoke test)
- Are external services reachable? (email, payment, etc.)
- Are monitoring and logging running? (Logs appear, metrics are collected)
C. Immediate Rollback on Smoke Test Failure If a smoke test fails:
- Immediately initiate rollback (according to the rollback plan from PREPARE.md)
- Document the failure
- Mark deployment as failed
- Analyse the cause before the next deployment attempt
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.
- 1mo ago Changed · +3 lines 9a623c86b948
- 2mo ago Changed 141785490a36
- 2mo ago First seen · 115 lines · 0 tokens per session scan A d07395c38159
p7-deploy is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,378 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.
p7-deploy compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| p7-deployjonase47/ccpr | Command | 1 | 1mo ago | MIT | A | 0 | Claude Code |
| firebase-publishPierry/harness-kit | Command | 4 | 1mo ago | MIT | A | 20 | Claude Code |
| statsAR6420/Hail_Hydra | Command | 51 | 7d ago | MIT | A | 29 | Claude Code |
| debugjoaquimscosta/arkhe-claude-plugins | Command | 22 | 23d ago | MIT | A | 48 | Claude Code |
| forge-compact-taskluiseiman/dotforge | Command | 8 | 3d ago | MIT | A | 46 | Claude Code |
| forge-resetluiseiman/dotforge | Command | 8 | 3d ago | MIT | A | 15 | Claude Code |
| _conventionsbuild-with-dhiraj/ai-workflow-framework-portability-kit | Command | 5 | 1mo ago | MIT | A | 0 | Claude Code |