release

release is a skill for Claude Code, Codex from jketreno/clare. It costs 29 tokens per session (855 once invoked), scanned A, original, MIT.

A release-preparation workflow for a software repository that audits documentation, updates release notes, and hands the final publishing step to a person.

In plain words
What is it for?
Use it to prepare version information and changelog updates, verify the repository and CI checks, commit and push the preparation changes, and leave signed publishing for a human.
Why use it?
It checks that release instructions match the actual scripts and that required checks pass before release work is handed off.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/jketreno/clare/release
Any agent
npx skills add jketreno/clare --skill release
Clone the repo
git clone --depth 1 https://github.com/jketreno/clare

Made for: Claude Code, Codex.

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/jketreno/clare/release.svg)](https://agentmods.dev/skills/jketreno/clare/release)
Your own site
<a href="https://agentmods.dev/skills/jketreno/clare/release"><img src="https://agentmods.dev/badge/skills/jketreno/clare/release.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 855 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00029 $0.00855
Opus 5 $0.00015 $0.00428
Sonnet 5 $0.00006 $0.00171
Haiku 4.5 $0.00003 $0.00085

Measured 5d ago against content hash f0ab7ded9a86, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

Makes network callslowCapability

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

curl -fsSLO https://github.com/jketreno/clare/releases/download/vX.Y.Z/clare-installer-vX.Y.Z.sh
.codex/skills/release/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLARE Repo Skill: Prepare a Release

Use this skill when a user asks to prepare or cut a release for this repository. This skill does not publish the release directly.

Non-negotiables

  1. Git tree must be clean before starting.
  2. Release must run from main.
  3. ./clare/verify-ci.sh must pass before handoff.
  4. Before release prep, audit docs for command/flag accuracy by inspecting scripts.
  5. If docs and implementation disagree, abort prep and report a mismatch summary.
  6. Update release collateral, then stage, commit, and push before handoff.
  7. Do not run ./scripts/release.sh automatically because signing requires manual passphrase entry.
  8. Update README release version block by replacing only the content between:
    • <!-- RELEASE_VERSION_START -->
    • <!-- RELEASE_VERSION_END -->
  9. The updated block must include:
    • the new version label vX.Y.Z
    • a link to https://github.com/jketreno/clare/releases/tag/vX.Y.Z
    • install commands with exact installer filename for that version

Phase 1: Preflight + Accuracy Audit

Run:

git status --porcelain
git branch --show-current
./clare/verify-ci.sh

Inspect script capabilities and compare with README/docs references:

./scripts/release.sh --help
./scripts/clare-installer.sh --help

Verify README and all files under docs/ only reference supported commands and flags.

Abort criteria:

  • Any command in README/docs uses unsupported script flags
  • Any release instructions refer to removed scripts
  • Any required prerequisites are outdated or missing

If aborting, provide a concise mismatch summary with file paths and exact incorrect command snippets.

Phase 2: Changelog Update

Determine the release baseline:

LAST_TAG="$(git tag -l 'v*' --sort=-version:refname --merged HEAD | head -1)"

If LAST_TAG exists, summarize user-relevant changes from LAST_TAG..HEAD. If no tag exists, summarize user-relevant changes from repo start.

Update CHANGELOG.md with:

  • new release heading vX.Y.Z
  • concise user-facing summary of features/fixes/behavior changes
  • no internal-only noise unless it affects users

Read the full file on GitHub · 118 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. 5d ago First seen · 118 lines · 29 tokens per session scan A f0ab7ded9a86

Subscribe to this mod's changes

release is a skill published in the GitHub repository jketreno/clare (5 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 855 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.