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.
git clone --depth 1 https://github.com/xonika9/agent-skillsnpx agentmods add skills/xonika9/agent-skills/releaseWrote 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/xonika9/agent-skills/release)<a href="https://agentmods.dev/skills/xonika9/agent-skills/release"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/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/xonika9/agent-skills/release"><img src="https://agentmods.dev/badge/skills/xonika9/agent-skills/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 | $0.00069 | $0.01912 |
| Opus 5.5 | $0.00028 | $0.00765 |
| Sonnet 5.5 | $0.00014 | $0.00382 |
| Haiku 4.5 | $0.00007 | $0.00191 |
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 5d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release
Prepare or publish a version of x9-agent-skills from the complete repository state. The latest public tag, the diff to the release candidate, CHANGELOG.md, both plugin manifests, the validation workflow, and the release workflow are the sources of truth; do not infer release scope from the current conversation or recent commits alone.
This is a private repository-local skill. Its canonical source is .claude/skills/release; .agents/skills exposes that source through a repository-relative symlink. Do not add it to the public skills/ package or its manifests and READMEs.
Select the mode
- Prepare applies when the request is to prepare a release. Determine the calendar version, update release files, and run the release gate. Stop before commit, push, tag, or GitHub Release.
- Publish applies only when the maintainer explicitly asks to publish or release. It includes preparation, a release commit, a push to
main, and monitoring until the matching GitHub Release is visible or a concrete failure is reported.
An ordinary request to commit, push, merge, edit the changelog, or validate the package is not release authority. Never create or move a tag manually; .github/workflows/release.yml owns tag and GitHub Release creation after the pushed main commit passes validation.
Establish the candidate
Resolve the repository root from this skill's location, then inspect:
- the worktree, current branch, remotes, and latest public
v*tag; - the complete diff and commit range from that tag to the candidate, including uncommitted and untracked files;
README.md,README.ru.md,CHANGELOG.md,.claude-plugin/plugin.json,.codex-plugin/plugin.json;- the installed personal
~/.config/opencode/AGENTS.md,~/.claude/CLAUDE.md, and~/.codex/AGENTS.mdplus their published sources inglobal-files/; scripts/prepare_release.py,.github/workflows/validate.yml, and.github/workflows/release.yml.
Preserve unrelated and user-owned changes. If the candidate cannot be separated from unrelated work, the current branch cannot safely produce the intended main release, or the remote state conflicts with the local history, stop and report the exact blocker instead of rewriting history, discarding files, merging, or force-pushing.
What ships with it
4 files 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.
- 5d ago Changed · -1 lines dee8e7d037a0
- 11d ago Changed de1fc89eee2d
- 12d ago Changed · +6 lines b8a90da9e4eb
- 1mo ago First seen · 94 lines · 69 tokens per session scan A 0d2f117a7829
release is a skill published in the GitHub repository xonika9/agent-skills (4 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 1,912 once invoked, about $0.0003 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
antigravity-maintainer-batch-release
Run protected AAS maintainer sweeps, PR merge batches, resumable review, immutable distribution, Core checks, and scripted releases. Use for repository maintenance, main alignment, CLI/MCP/Workbench changes, or release work; not ordinary contribution tasks.
app-store-changelog
Generate user-facing App Store release notes from git history since the last tag.
write-release-notes
Generate engaging, high-energy release notes for a given version tag. Fetches the release from GitHub, retrieves every linked PR's title and description, then synthesizes all changes into a polished, user-facing release note with an enthusiastic tone. Use when the user asks to write, generate, or create release notes…
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
upgrade
Use this when you receive an [Upgrade Event: x.y.z→a.b.c] lick — fired on boot whenever the bundled SLICC version differs from the previous run. The lick renders a binary action card: lickconfirm to Update workspace files (three-way merge of bundled vfs-root files against the user's local edits) or lickdismiss to…
production-deployment-phase
Executes production deployment workflow by promoting validated staging builds to production with semantic versioning, health checks, and release tagging. Use when running /ship-prod command, deploying to production after staging validation, or promoting staging builds to production environment.