release

release is a skill for Claude Code from hanamizuki/solopreneur. It costs 205 tokens per session (5,462 once invoked), scanned A, original, MIT.

A manual release workflow for a marketplace containing multiple coding-agent plugins. It finds changed plugins, checks related documentation, and prepares version tags and release changes with user confirmation.

In plain words
What is it for?
Use it to inspect plugin changes since the last release, decide patch or minor version increases, update release information, and create tags for publishing.
Why use it?
It reduces the chance of releasing the wrong plugins, missing documentation updates, or choosing unintended version changes. It also prevents releases from starting with uncommitted work.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/generate-plugin-packages.sh.

Good fit Use it to inspect plugin changes since the last release, decide patch or minor version increases, update release information, and create tags for publishing.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/hanamizuki/solopreneur
agentmods
npx agentmods add skills/hanamizuki/solopreneur/release

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/hanamizuki/solopreneur/release/github.svg)](https://agentmods.dev/skills/hanamizuki/solopreneur/release)
Your own site
<a href="https://agentmods.dev/skills/hanamizuki/solopreneur/release"><img src="https://agentmods.dev/badge/skills/hanamizuki/solopreneur/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/hanamizuki/solopreneur/release"><img src="https://agentmods.dev/badge/skills/hanamizuki/solopreneur/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 205 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,462 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 $0.00205 $0.05462
Opus 5 $0.00102 $0.02731
Sonnet 5 $0.00041 $0.01092
Haiku 4.5 $0.00020 $0.00546

Measured 9d ago against content hash 59282b5b9ec7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 9d 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 · 495 lines

How it starts

The opening of the file, as written. The whole thing — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

Manual release flow for the solopreneur multi-plugin marketplace. Implements the release rule documented in CLAUDE.md at the repo root.

This skill is interactive. Confirm each decision with the user. Do not autopilot version bumps or release publishing.

Pre-flight

  1. Confirm cwd is the repo root or a worktree of it. Run from the directory containing .claude-plugin/marketplace.json, skills/, and src/.

  2. Confirm working tree is clean:

    git status --porcelain
    

    If unclean, stop and ask the user to commit or stash first. Don't release on top of uncommitted work. The new commit's content depends on the working tree.

  3. Confirm we're on main (the typical release path is "merge → release"):

    git branch --show-current
    

    If not on main, ask the user to confirm the branch is intentional.

  4. Pull latest:

    git fetch origin && git pull --ff-only
    

    If --ff-only fails (local has commits), stop and ask the user.

Step 1: Detect per-plugin changes since last tag

For each sub-plugin, find its last <plugin>--v* tag and compare against HEAD. Plugin names match the first-level directory names under both canonical roots.

PLUGINS=(solopreneur designer marketer ios-dev android-dev ai-engineer neo4j-dev)
for p in "${PLUGINS[@]}"; do
  LAST_TAG=$(git tag -l "${p}--v*" --sort=-v:refname | head -1)
  # Transitional fallback: the v0.5.x → v0.5.3 rename dropped the `solo-`
  # prefix from sub-plugins. The first /release run after that rename has
  # no `<bare>--v*` tag yet, so look for the legacy `solo-<bare>--v*` tag
  # to avoid a misleading "NO TAG YET" message. Once the new tag exists,
  # this fallback never fires again.
  if [ -z "$LAST_TAG" ] && [ "$p" != "solopreneur" ]; then
    LAST_TAG=$(git tag -l "solo-${p}--v*" --sort=-v:refname | head -1)
  fi
  if [ -z "$LAST_TAG" ]; then
    echo "=== $p: NO TAG YET (first release) ==="
    git log --oneline -- "skills/$p/" "src/$p/"
    continue
  fi
  CHANGED=$(git diff --name-only "$LAST_TAG"..HEAD -- "skills/$p/" "src/$p/" | wc -l | tr -d ' ')
  if [ "$CHANGED" -gt 0 ]; then
    echo "=== $p: $CHANGED files changed since $LAST_TAG ==="
    git log --oneline "$LAST_TAG"..HEAD -- "skills/$p/" "src/$p/"
  else
    echo "=== $p: no changes since $LAST_TAG ==="
  fi
done

Read the full file on GitHub · 495 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. 9d ago First seen · 495 lines · 205 tokens per session scan A 59282b5b9ec7

Subscribe to this mod's changes

release is a skill published in the GitHub repository hanamizuki/solopreneur (148 stars, last pushed 23d ago), licensed MIT. It adds 205 tokens to every session and 5,462 once invoked, about $0.0010 per session on Opus 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.