Borrowing it
Nothing to install: this file belongs to matteocervelli/llms. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/matteocervelli/llms/main/.claude/skills/release/SKILL.mdgit clone --depth 1 https://github.com/matteocervelli/llmsWrote 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/matteocervelli/llms/release)<a href="https://agentmods.dev/skills/matteocervelli/llms/release"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/release.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.00849 |
| Opus 5 | $0.00035 | $0.00425 |
| Sonnet 5 | $0.00014 | $0.00170 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Skill
Unified entry point for all release operations. Delegates to the right subcommand template based on the first argument.
Subcommands
| Command | What it does |
|---|---|
/release plan |
Scope version, analyze milestones/issues/tags, create GitHub milestone |
/release verify [commits|tags|history] |
Integrity checks: commit↔CHANGELOG, tag↔releases↔artifacts, history audit |
/release changelog |
Generate CHANGELOG entries + version bump propagation across manifest files |
/release full |
Full orchestrator: plan → health → fix blockers → docs → tag+ship |
/release |
Auto-detect what's needed (see below) |
Auto-Detection (no subcommand)
LAST_TAG=$(git describe --tags --abbrev=0 --match "v*" 2>/dev/null)
UNRELEASED=$(git log --no-merges --oneline "${LAST_TAG:-$(git rev-list --max-parents=0 HEAD)}..HEAD" | wc -l)
OPEN_MILESTONE=$(gh api "repos/$(gh repo view --json nameWithOwner --jq '.nameWithOwner')/milestones" \
--jq '[.[] | select(.state=="open")] | length' 2>/dev/null || echo 0)
CLOSED_ISSUES=$(gh api "repos/$(gh repo view --json nameWithOwner --jq '.nameWithOwner')/milestones" \
--jq '[.[] | select(.state=="open" and .open_issues==0)] | length' 2>/dev/null || echo 0)
Decision tree:
- Milestone exists with 0 open issues → suggest
/release full - Unreleased commits > 0, no milestone → suggest
/release plan - Clean main, recent tag → suggest
/release verify tags - Default → show the subcommand table above and ask what's needed
Execution
Load the template matching the subcommand and follow it completely:
plan→~/.claude/skills/release/templates/plan.mdverify→~/.claude/skills/release/templates/verify.mdchangelog→~/.claude/skills/release/templates/changelog.mdfull→~/.claude/skills/release/templates/cycle.md
What ships with it
6 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.
- 3d ago First seen · 60 lines · 70 tokens per session scan A 88f675376017
release is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 849 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
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.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
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.
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.
updater_guide
Guidance for checking for and installing Row-Bot updates.