Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add YoungjaeDev/my-claude-plugins --skill releasegit clone --depth 1 https://github.com/YoungjaeDev/my-claude-pluginsWrote 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.
[](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/release)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/release"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/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.
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/release"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.02620 |
| Opus 5.5 | $0.00051 | $0.01048 |
| Sonnet 5.5 | $0.00025 | $0.00524 |
| Haiku 4.5 | $0.00013 | $0.00262 |
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 25d 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.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
Create a versioned GitHub release: detect the current version, update the version manifests, commit, tag, push, and let gh release create --generate-notes write the release-page notes. The repository's CHANGELOG.md is not this skill's file — dev:post-merge Step 9.5 and docs:changelog own it.
Guidelines
- Interactive input is capability-aware. Every prompt and confirmation below is a gate, not one hardcoded tool:
AskUserQuestionunder Claude Code,request_user_inputunder Codex where exposed, otherwise one concise blocking question asked before the irreversible action (the tag, the push,gh release create). Full policy:AGENTS.md→ "Cross-runtime interactive input policy". - The tag and the release are public and irreversible. Never run Steps 8-9 without the Step 5 confirmation, and never publish a tag this run did not create.
Arguments
- Version (optional): Explicit version string, e.g.,
1.2.0 --patch/--minor/--major: Semver bump shorthand (overrides auto-detection)--dry-run: Preview version bump and changelog without creating anything--draft: Create as draft release on GitHub--prerelease: Mark as pre-release on GitHub--skip-validation: Skip build/test verification before releasing--init <commit>: Create initial baseline tag (for first-ever release)
Workflow
-
Check Prerequisites
- Verify
ghCLI is installed and authenticated:gh auth status - Verify clean working tree:
git status --porcelain- If uncommitted changes exist, prompt user to commit or stash first
- Verify current branch is pushed to remote:
git rev-parse --abbrev-ref --symbolic-full-name @{u}. No upstream means the tag would point at a commit GitHub cannot see — stop and have the user push the branch first.
- Verify
-
Detect Previous Tag
- Run
git fetch --tagsand thengit tag --list 'v[0-9]*' | grep -E '^v[0-9]+\.[0-9]+\.[0-9]+$' | sort -t. -k1.2,1n -k2,2n -k3,3n | tail -1to find the highest existing release tag; the strictvX.Y.Zfilter keepsv2, pre-release and nightly tags out of the pick. Do not usegit describe --tags --abbrev=0: it returns the nearest tag reachable from HEAD, which is not the latest version whenever a higher tag lives on another branch — and that single value feeds both the bump base and--notes-start-tag. - If no tags exist:
- If
--init <commit>provided: create baseline tag at specified commitgit tag v0.0.0 <commit> - If
--initnot provided: prompt user with options:- Tag current HEAD as
v0.0.0(baseline only, no release) - Tag a specific commit as baseline
- Abort and let user set up tags manually
- Tag current HEAD as
- After baseline created, re-run detection
- If
- Run
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 25d ago Changed 6b8a0cf219c4
- 1mo ago Changed · +36 lines b400899d630e
- 1mo ago Changed · -1 tokens per session 1d12c355412e
- 2mo ago First seen · 194 lines · 128 tokens per session scan A c99350c55169
release is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 2,620 once invoked, about $0.0005 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.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
release
Fully automate a release with version-bump and childhood.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.