episko: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from respeak-io/episko. It costs 0 tokens per session (2,998 once invoked), scanned A, original, MIT.

A release skill for the Episko project. A release is a prepared software version made available to users; this procedure merges approved changes, runs checks, updates the changelog, creates a version tag, and synchronizes branches.

In plain words
What is it for?
Use it to cut, ship, tag, or prepare an Episko release, including merging pull requests and running the required gates.
Why use it?
It turns the project's release process into a fixed sequence with human approval at specified stopping points. It helps avoid publishing from the wrong branch or account.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; positional $N argument; mentions Claude Code.

This is respeak-io/episko's own configuration. It tells Claude Code how to work on episko 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 episko configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/changelog.mjs release <x.y.z>.

Reuse

Borrowing it

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

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/respeak-io/episko/release/github.svg)](https://agentmods.dev/skills/respeak-io/episko/release)
Your own site
<a href="https://agentmods.dev/skills/respeak-io/episko/release"><img src="https://agentmods.dev/badge/skills/respeak-io/episko/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/respeak-io/episko/release"><img src="https://agentmods.dev/badge/skills/respeak-io/episko/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,998 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.02998
Opus 5.5 $0.00000 $0.01199
Sonnet 5.5 $0.00000 $0.00600
Haiku 4.5 $0.00000 $0.00300

Measured 1mo ago against content hash 8f59a479f2e2, 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 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- episko.dev: `curl -s https://episko.dev | grep -o 'data-ver>v[0-9.]*'`. Check the **served
.claude/skills/release/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cutting a release

RELEASE.md is the procedure; this file is only the driver. It holds the click-through checklist, what CI already guarantees, and the reasoning behind each step. Read it at step 4 rather than restating it here — a second copy of a checklist drifts from the first, and the repo has shipped that failure twice already (health.rs vs health.ts, and the two hand-kept status-letter tables that each claimed to be shared with the other). When this file and RELEASE.md disagree, RELEASE.md wins and gets fixed in the same commit.

Work top to bottom. Steps 1, 3, 4 and 7 are STOP points — do not pass one without an answer from the human. Everything between them is mechanical and takes about ten minutes, which is what the release history shows: every release: commit since 0.13.x lands within two minutes of its merge commit.


0. Preflight

gh auth status                 # FAbrahamDev must be the ACTIVE account
git fetch origin --prune --tags
git rev-list --count origin/dev..origin/main      # must be 0
  • Two GitHub accounts are logged in on this machine. Blaxzter is the wrong one for respeak-io/episko; gh pr create under it fails or files against the wrong identity.
  • The count must be 0, meaning main is an ancestor of dev. Anything else means the last release skipped step 9 and dev is about to re-propose notes that already shipped.
  • Local main is usually far behind — it is only touched at release time. Never assume it.

1. STOP — which PRs go in

An open PR is not a release candidate. Never merge the list because it is the list: it routinely holds work nobody is shipping today, and two entries are near-certain traps — the branch the human is standing on (git branch --show-current, their own work in flight) and any PR that is itself part of this release effort. At 0.30.0 there were six open and two were exactly those.

Show the list and ask which ones go in. Ask even when the answer looks obvious, and ask again if the human says "all" while a draft or their own current branch is in it.

Read the full file on GitHub · 236 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. 1mo ago Changed · +4 lines 8f59a479f2e2
  2. 1mo ago Changed · +7 lines c6e2c1ff157a
  3. 1mo ago First seen · 225 lines · 0 tokens per session scan A 35b09bffb851

Subscribe to this mod's changes

release is a skill published in the GitHub repository respeak-io/episko (19 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,998 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-24.

Related

release compared with skills from other repositories

release next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
releaserespeak-io/episkoSkill19yesterdayMITA0Claude Code
release-announcementpaperclipai/paperclipSkill111kyesterdayMITA42Claude Code, Codex
releasethedotmack/claude-memSkill114kyesterdayApache-2.0A13Claude Code
release-notesphuryn/pm-skillsSkill28k8d agoMITA57Claude Code
multi-agent-release-managerchromium/chromiumSkill25kyesterdayBSD-3-ClauseA27Claude Code, Codex
pack-submitaeonfun/aeonSkill788yesterdayMITA27Claude Code, Codex
updater_guidesiddsachar/row-botSkill1.7kyesterdayApache-2.0A22Claude Code, Codex