jumpstarter: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from jumpstarter-dev/jumpstarter. It costs 21 tokens per session (5,588 once invoked), scanned A, original, Apache-2.0.

A release-process guide for the Jumpstarter project, covering the steps for preparing branches, version tags, package metadata, and an operator bundle.

In plain words
What is it for?
Use it when creating release candidates or final releases, updating FLS versions, and preparing operator bundle changes.
Why use it?
It helps prevent inconsistent version names and missed release updates across the project and related repositories.

Skill for Claude Code

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

This is jumpstarter-dev/jumpstarter's own configuration. It tells Claude Code how to work on jumpstarter 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 jumpstarter configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is cd ../community-operators-prod.

Reuse

Borrowing it

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

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jumpstarter-dev/jumpstarter/release"><img src="https://agentmods.dev/badge/skills/jumpstarter-dev/jumpstarter/release.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 5,588 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: 3 findings, 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 296
    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.
  • medium Excessive Agency · line 416
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 417
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 $0.00021 $0.05588
Opus 5.5 $0.00008 $0.02235
Sonnet 5.5 $0.00004 $0.01118
Haiku 4.5 $0.00002 $0.00559

Measured 2mo ago against content hash 11a882a7d969, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release 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/SKILL.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jumpstarter Release

You are guiding the user through the Jumpstarter project release process.

Before proceeding, read .claude/rules/releasing-operator.md for operator-specific details.

Release input: $ARGUMENTS

Conventions

  • Git tags use a v prefix: v0.8.1, v0.9.0-rc.1
  • Container image tags do NOT use a v prefix: :0.8.1, :0.9.0-rc.1
  • RC tag format: vX.Y.Z-rc.N (with dot before N). Reject old formats like rc1 or -rc1.
  • RC-first rule: When a release branch has no final release tags yet, the first tag MUST be an RC. Never tag a direct vX.Y.0 final on a new branch without at least one RC first.
  • FLS tags do NOT use a v prefix: 0.3.0, 0.4.0 (repo: jumpstarter-dev/fls)
  • Python packages are versioned automatically from git tags via hatch-vcs — no manual version files.
  • The bundle/ directory is NOT committed to the repo.
  • GITHUB_USER env var controls the fork for community-operators and for pushing version-bump PRs. Auto-detected via gh api user -q .login if not set.
  • Do NOT modify controller/deploy/operator/api/v1alpha1/jumpstarter_types.go — the operator resolves :latest image defaults to its own version at runtime.

Ordering constraint

[optional FLS release] → Makefile/FLS pin update → commit → tag push → GitHub Release / [CI builds images] → make bundle → make contribute

If a new FLS version is needed, release FLS first so binaries exist before Jumpstarter CI builds the exporter image. Images must exist before bundle generation. The skill enforces this by splitting the process into phases.

Steps

1. Gather context and determine release type

Fetch the latest remote state and detect the GitHub user early:

GITHUB_USER="${GITHUB_USER:-$(gh api user -q .login)}"
echo "GitHub user: $GITHUB_USER"

git fetch origin --tags
git branch --show-current
git branch -r | grep 'origin/release-'
git tag --sort=-version:refname | head -20
gh release list --limit 5
grep -E '^(VERSION|REPLACES) ' controller/deploy/operator/Makefile
# Current FLS pins in Jumpstarter
grep -E 'ARG FLS_VERSION=' python/Containerfile
rg -n 'fls_version: str = "|--fls-version"' \
  python/packages/jumpstarter-driver-flashers/jumpstarter_driver_flashers/client.py

Read the full file on GitHub · 478 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 · 478 lines · 21 tokens per session scan A 11a882a7d969

Subscribe to this mod's changes

release is a skill published in the GitHub repository jumpstarter-dev/jumpstarter (233 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 5,588 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 2026-08-30.

Related

release compared with skills from other repositories

release next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
releasejumpstarter-dev/jumpstarterSkill233yesterdayApache-2.0A21Claude Code
github-release-managementruvnet/RuViewSkill103kyesterdayMITA27Claude Code
agent-github-modesruvnet/rufloSkill81kyesterdayMITA21Claude Code
xberg-releasexberg-io/xbergSkill9.5kyesterdayMITA16Claude Code, Codex
factory-shipBuilderIO/skillsSkill4.6k4d agoMITA28Claude Code
releaseprcompozy/compozySkill2.8kyesterdayMITA53Claude Code, Codex
gitlab-devopsautomateyournetwork/netclawSkill715yesterdayApache-2.0A67Claude Code, Codex