nxtcm-components: Skill for Claude Code

.agents/skills/pr-release-agent/SKILL.md

pr-release-agent is a skill for Claude Code, Codex from RedHatInsights/nxtcm-components. It costs 75 tokens per session (3,337 once invoked), scanned A, original, Apache-2.0.

A workflow for creating a GitHub pull request, which proposes code changes for review before they are merged.

In plain words
What is it for?
Use it when you want to turn your own local commits and edits into a reviewed pull request using the GitHub command-line tool.
Why use it?
It removes the repetitive work of checking your changes, writing the request from the project template, pushing the branch, and opening the request.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is RedHatInsights/nxtcm-components's own configuration. It tells Claude Code and Codex how to work on nxtcm-components 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 nxtcm-components configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RedHatInsights/nxtcm-components. 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/RedHatInsights/nxtcm-components/main/.agents/skills/pr-release-agent/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/RedHatInsights/nxtcm-components

Made for: Claude Code, Codex.

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 pr-release-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhatinsights/nxtcm-components/pr-release-agent/github.svg)](https://agentmods.dev/skills/redhatinsights/nxtcm-components/pr-release-agent)
Your own site
<a href="https://agentmods.dev/skills/redhatinsights/nxtcm-components/pr-release-agent"><img src="https://agentmods.dev/badge/skills/redhatinsights/nxtcm-components/pr-release-agent/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 pr-release-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhatinsights/nxtcm-components/pr-release-agent"><img src="https://agentmods.dev/badge/skills/redhatinsights/nxtcm-components/pr-release-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,337 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 $0.00075 $0.03337
Opus 5.5 $0.00030 $0.01335
Sonnet 5.5 $0.00015 $0.00667
Haiku 4.5 $0.00007 $0.00334

Measured yesterday against content hash df6f67ba0694, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pr-release-agent 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 yesterday.

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.

.agents/skills/pr-release-agent/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Release Agent

Automates the full PR lifecycle: analyze changes, draft a description that fills the project PR template, push, create the PR, and clean up.

Prerequisites

  • gh CLI installed and authenticated (gh auth status)

Workflow

Track progress with this checklist:

PR Release Progress:
- [ ] Step 1: Gather context
- [ ] Step 2: Draft PR description & generate title
- [ ] Step 3: Save draft to pr_draft.md
- [ ] Step 4: Validate (build, lint, tests)
- [ ] Step 5: Stage and commit changes
- [ ] Step 6: Push branch to origin
- [ ] Step 7: Create or update PR via gh CLI
- [ ] Step 8: Clean up pr_draft.md

Step 1 — Gather context

Author scope — required

The PR title, Description, Focus Areas, and checkbox inferences must reflect only work authored by the person running the workflow (plus any unstaged/staged edits still on disk). Do not summarize, quote, or paraphrase commit messages from other contributors—even if those commits sit ahead of the integration branch.

  1. Resolve the author identity (read-only):

    AUTHOR_EMAIL="$(git config user.email)"
    

    If AUTHOR_EMAIL is empty, stop and tell the user to set user.email (or run the workflow after configuring it). Do not change git config — see Important notes.

  2. Record the integration branch and compute the merge base. Default to main unless the user named a different target branch in their request:

    INTEGRATION_BRANCH="main"   # substitute the user-specified branch if provided
    MB="$(git merge-base "${INTEGRATION_BRANCH}" HEAD)"
    

    Reuse INTEGRATION_BRANCH (never the hard-coded string main) for every subsequent git log range, gh pr create --base, and history checks in this workflow.

Run these commands in parallel with the usual housekeeping (branch, status):

git branch --show-current
git status --short
git diff
git diff --cached

Commits and patches authored by AUTHOR_EMAIL only — use these for narrative scope (titles, bullets, Focus Areas). --author is a regular expression; --fixed-strings matches the string literally; wrapping the email in <…> pins it to the email-address boundary in the commit author field, preventing partial matches against other addresses that share a prefix:

Read the full file on GitHub · 298 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. yesterday Changed · +63 lines df6f67ba0694
  2. 1mo ago Changed 693995707ae2
  3. 2mo ago First seen · 235 lines · 75 tokens per session scan A a21eb9d4db7b

Subscribe to this mod's changes

pr-release-agent is a skill published in the GitHub repository RedHatInsights/nxtcm-components (10 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 3,337 once invoked, about $0.0003 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 2026-08-31.