rangeLink: Skill for Claude Code

.claude/skills/release-prep/SKILL.md

release-prep is a skill for Claude Code from couimet/rangeLink. It costs 0 tokens per session (1,218 once invoked), scanned A, original, MIT.

A release-tracking procedure for the RangeLink VS Code extension after the release-lock step has run. It creates the remaining GitHub issue for registering an article on couimet.github.io and adds it to the release board.

In plain words
What is it for?
It helps finish release records for a specified version by checking the lock output, reading the QA and Dev.to issue URLs, creating the article-registration issue, and reporting all three URLs.
Why use it?
It fills the final tracking step and brings the required release issues together with their links.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is couimet/rangeLink's own configuration. It tells Claude Code how to work on rangeLink 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 rangeLink configures →

Reuse

Borrowing it

Nothing to install: this file belongs to couimet/rangeLink. 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/couimet/rangeLink/main/.claude/skills/release-prep/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/couimet/rangeLink

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 release-prep

README.md
[![agentmods](https://agentmods.dev/badge/skills/couimet/rangelink/release-prep/github.svg)](https://agentmods.dev/skills/couimet/rangelink/release-prep)
Your own site
<a href="https://agentmods.dev/skills/couimet/rangelink/release-prep"><img src="https://agentmods.dev/badge/skills/couimet/rangelink/release-prep/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 release-prep

Your own site · 80×15
<a href="https://agentmods.dev/skills/couimet/rangelink/release-prep"><img src="https://agentmods.dev/badge/skills/couimet/rangelink/release-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,218 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.01218
Opus 5.5 $0.00000 $0.00487
Sonnet 5.5 $0.00000 $0.00244
Haiku 4.5 $0.00000 $0.00122

Measured 2mo ago against content hash 563d1d3b3544, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-prep 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 2mo 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/skills/release-prep/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release Prep

Finish the GitHub tracking artifacts for a release of the VS Code extension after the release lock workflow has run. The lock script (pnpm release:lock:vscode-extension X.Y.Z) creates the QA issue and the dev.to issue and adds them to the release board; this skill creates the remaining cross-repo couimet.github.io article-registration issue, adds it to the board, and reports all three URLs.

Input: X.Y.Z target version (e.g., /release-prep 2.1.0)

Step 1: Verify the release lock completed

The lock workflow must have run first; its console summary prints this skill prompt. Confirm its state:

  • packages/rangelink-vscode-extension/qa/release-testing-instructions-vX.Y.Z.md exists
  • Its frontmatter contains both qa_issue_url: and devto_issue_url: with real URLs

If either check fails, stop and print: run pnpm release:lock:vscode-extension X.Y.Z first, then re-run this skill.

Step 2: Read the issue URLs from the instructions frontmatter

Extract both URLs from the frontmatter of packages/rangelink-vscode-extension/qa/release-testing-instructions-vX.Y.Z.md:

  • QA issue URL: the value of qa_issue_url
  • Dev.to issue URL: the value of devto_issue_url

These are the issues the lock script created and already added to the release board.

Step 3: Check for an existing cross-repo issue

The article-registration issue lives in couimet/couimet.github.io. Check for an existing open issue with an exact title match before creating a new one, capturing the URL when one exists:

EXISTING_ISSUE_URL=$(gh issue list \
  --repo couimet/couimet.github.io \
  --state open \
  --search "Register RangeLink X.Y.Z article on the site in:title" \
  --json title,url --limit 100 \
  --jq '.[] | select(.title == "Register RangeLink X.Y.Z article on the site") | .url' \
  | head -1)

The --jq filter selects only an issue whose title EXACTLY matches Register RangeLink X.Y.Z article on the site, and --limit 100 covers the full expected result set; together they guard against an older open issue with a similar title being misidentified as this release's registration issue. If $EXISTING_ISSUE_URL is non-empty, reuse that exact URL for the Step 5 board step and the Step 6 report and skip creation, preserving the skill's re-runnability. Step 4 (creation) runs only when no exact match was found.

Read the full file on GitHub · 89 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. 2mo ago First seen · 89 lines · 0 tokens per session scan A 563d1d3b3544

Subscribe to this mod's changes

release-prep is a skill published in the GitHub repository couimet/rangeLink (10 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,218 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 2026-08-31.

Related

Other skills, from other repositories

omh-release-cut

This is an OMH release-cut workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 92 tokens

omh-deploy-and-monitor

This is an OMH deploy-and-monitor workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 65 tokens

git-wrapup

Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…

cyanheads/obsidian-mcp-server · 109 tokens

release-and-publish

Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…

cyanheads/obsidian-mcp-server · 155 tokens

release-pr-review

Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…

cyanheads/obsidian-mcp-server · 136 tokens

release-rollback

Plan and execute authorized release promotion or rollback with exact artifact and data compatibility. Use when deploying versions, changing traffic or recovering a bad release; do not equate reversing code with restoring data.

WrongStack/WrongStack · 42 tokens