deploy-pr

deploy-pr is a skill for Claude Code from tomzx/agents. It costs 21 tokens per session (1,137 once invoked), scanned A, original, MIT.

A deployment workflow for a merged pull request, which is a proposed code change already accepted into a repository. It deploys the change, runs smoke tests, checks health, and uses rollback when deployment fails.

In plain words
What is it for?
Use it to deploy a merged change, identify its environment, confirm or document rollback steps, run basic production checks, and revert a failed deployment.
Why use it?
It closes the gap between merging code and confirming that the change works in the target environment.

Skill for Claude Code

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

Good fit Use it to deploy a merged change, identify its environment, confirm or document rollback steps, run basic production checks, and revert a failed deployment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/deploy-pr
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.

Any agent
npx skills add tomzx/agents --skill deploy-pr
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

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 deploy-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/deploy-pr/github.svg)](https://agentmods.dev/skills/tomzx/agents/deploy-pr)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/deploy-pr"><img src="https://agentmods.dev/badge/skills/tomzx/agents/deploy-pr/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 deploy-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/deploy-pr"><img src="https://agentmods.dev/badge/skills/tomzx/agents/deploy-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,137 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 $0.01137
Opus 5.5 $0.00008 $0.00455
Sonnet 5.5 $0.00004 $0.00227
Haiku 4.5 $0.00002 $0.00114

Measured 22d ago against content hash 32c64eaf2b29, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deploy-pr 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 22d 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.

skills/deploy-pr/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy PR

Deploys a merged pull request to the target environment, runs smoke tests to verify the deployment, and confirms a rollback plan exists. Covers the step between merging code and having it running in production.

Prerequisites

  • Apply the shared SDLC conventions in skills/sdlc/references/shared.md.
  • If no argument is provided, target the pull request from $PR_NUMBER (and $REPO).
  • gh CLI authenticated with write access to the target repository
  • A merged PR number or merge SHA provided as $1
  • Deployment tooling available (CI/CD pipeline, container registry, or manual deployment scripts)
  • Read any files present under .sdlc/context/ for project-level context, especially architecture.md for deployment topology

Workflow

Fetch merged PR details ($1)
        |
        v
  Identify target environment
        |
        v
  Confirm rollback plan exists
     /         \
   Yes          No
    |            |
    v            v
  Execute     Document rollback
  deployment  procedure first,
    |         then proceed
    v
  Run smoke tests
     /         \
   Pass         Fail
    |            |
    v            v
  Verify      Execute rollback
  health      Report failure
    |            |
    v            v
  Report      Stop, investigate
  success

Steps

  1. Fetch the merged PR details:

    gh pr view $1 --json title,body,mergeCommit,headRefName,closingIssuesReferences
    
  2. Identify the target environment(s) from the PR labels, branch name, or project configuration. Common targets:

    • staging for non-production validation
    • production for user-facing releases
    • Feature-specific environments (e.g., preview, canary) If uncertain, ask the user which environment to deploy to.
  3. Check for a rollback plan. Look for:

    • A documented rollback procedure in the PR description or .sdlc/ artifacts
    • Previous deployment version or tag to roll back to
    • Database migration rollback if applicable If no rollback plan exists, document one before proceeding.

Read the full file on GitHub · 156 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. 22d ago Changed · +3 lines 32c64eaf2b29
  2. 24d ago Changed a4533c54e933
  3. 1mo ago First seen · 153 lines · 21 tokens per session scan A e23f63c8e638

Subscribe to this mod's changes

deploy-pr is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 1,137 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.