loope: Skill for Claude Code

.claude/skills/release-new-version/SKILL.md

release-new-version is a skill for Claude Code from ngthluu/loope. It costs 38 tokens per session (1,535 once invoked), scanned A, original, MIT.

A release procedure for the Loope project that compares the latest version tag with the current code, creates grouped release notes, then tags and pushes a new release.

In plain words
What is it for?
Use it when preparing a new Loope release, checking repository readiness, writing release notes, and publishing the chosen version tag.
Why use it?
It provides a repeatable release checklist and stops when the branch, working tree, repository sync, or GitHub access is not ready.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents.

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

Reuse

Borrowing it

Nothing to install: this file belongs to ngthluu/loope. 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/ngthluu/loope/main/.claude/skills/release-new-version/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ngthluu/loope

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-new-version

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ngthluu/loope/release-new-version"><img src="https://agentmods.dev/badge/skills/ngthluu/loope/release-new-version.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,535 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 12
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 $0.00038 $0.01535
Opus 5.5 $0.00015 $0.00614
Sonnet 5.5 $0.00008 $0.00307
Haiku 4.5 $0.00004 $0.00153

Measured 2mo ago against content hash e246170773d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-new-version 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-new-version/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cutting a loope release

Announce at start: "Using release-new-version to cut a release."

This procedure is stop and report, never unwind. If any step fails, say which step failed and what has already happened, then stop. Never run git reset, git tag -d, git push --force, gh release delete, git stash, git checkout, or git pull in this skill — not even to clean up after yourself. A half-finished run is safe to re-run.

Never propose a version number. The author types it.

Step 1 — Preflight

Run in one Bash call:

echo "branch: $(git rev-parse --abbrev-ref HEAD)"
echo "dirty: [$(git status --porcelain)]"
git fetch --tags origin
echo "divergence: $(git rev-list --left-right --count origin/main...HEAD)"
gh auth status

Stop if any of these hold, reporting exactly which check failed:

Check Stop if
On main branch is not main
Clean tree git status --porcelain output is non-empty
Synced with origin either number in the divergence count is non-zero
GitHub CLI ready gh auth status exited non-zero

Do not stash, reset, checkout, or pull on the author's behalf. Tell them what to fix and stop.

Step 2 — Establish the range

git describe --tags --abbrev=0
  • If this fails (no tags yet): the range is the full history — use HEAD as the range for the log/diff commands below, and introduce the note as the first release when you present it.
  • Otherwise the range is <latest>..HEAD.

Then:

git rev-list --count <range>

If the count is 0, report that there is nothing to release since <latest> and stop.

Step 3 — Collect the material

git log --no-merges --pretty=format:'%h %s%n%b---' <range>
git diff --stat <range>

Merge commits are excluded: this repo does not squash, so the PR merge commits carry nothing the branch commits do not. Use --stat, not the full diff — the commit subjects and bodies carry the intent, and the stat keeps the subagent input bounded.

Read the full file on GitHub · 177 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 · 177 lines · 38 tokens per session scan A e246170773d7

Subscribe to this mod's changes

release-new-version is a skill published in the GitHub repository ngthluu/loope (13 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 1,535 once invoked, about $0.0002 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 2026-08-30.