A release procedure for the mind command-line tool. It updates the version and changelog, checks the build and tests, creates a version tag, and starts the GitHub workflow that publishes platform binaries and updates the Homebrew formula.

Use it to prepare and publish a new mind release, choosing a major, minor, or patch version according to whether changes are breaking, feature-level, or bug fixes.

It provides a defined sequence for checking that a release is ready and for keeping its version, source tag, downloadable files, and Homebrew package aligned. It also guides the version increment based on the changes made.

How jaemk/mind configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jaemk/mind. 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/jaemk/mind/main/.claude/skills/release/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/jaemk/mind

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jaemk/mind/release/github.svg)](https://agentmods.dev/skills/jaemk/mind/release)

Your own site

<a href="https://agentmods.dev/skills/jaemk/mind/release"><img src="https://agentmods.dev/badge/skills/jaemk/mind/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jaemk/mind/release"><img src="https://agentmods.dev/badge/skills/jaemk/mind/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,112 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00064	$0.02112
Opus 5.5	$0.00026	$0.00845
Sonnet 5.5	$0.00013	$0.00422
Haiku 4.5	$0.00006	$0.00211

Measured 2d ago against content hash 29e2638ab910, 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 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 2d 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.

.claude/skills/release/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

release

Cut a release of mind. The version in Cargo.toml is the single source of truth, and merging a version bump to main is the release: every push to main runs .github/workflows/release.yml, whose decide job releases only when Cargo.toml carries a stable version (no -dev suffix) that has no GitHub release yet. The workflow then builds the per-platform binaries, creates the v<version> tag and the GitHub Release, publishes to crates.io, regenerates the Homebrew formula, and puts main back on the next -dev version. Nothing is pushed to main or tagged by hand.

Releases are SemVer. Pick the bump from what landed since the last tag: a new verb/flag or other backward-compatible feature is a minor bump; a bug-fix-only batch is a patch; a breaking change to the CLI, config, on-disk layout, or mind.toml schema is a major bump.

The bump goes in one of two places:

A release PR (default): a dedicated branch off main carrying only the bump and the changelog. Releases whatever has already landed on main.
An existing PR: a bump commit added on top of an open feature PR, so merging that PR lands the change and releases it in one step. Use this when asked to "release with PR N" or "add the version bump to this PR".

Steps

1. Get onto the branch

For a release PR, start from an up-to-date main on a new release branch:

git switch main
git pull
git status --porcelain                  # must print nothing
git switch -c YYMMDD.release-X.Y.Z      # today's date, the real version

For an existing PR, check out its branch and bring it up to date with main, so the version and changelog are bumped from what main carries now:

gh pr view <N> --json headRefName,mergeable
git switch <head branch>
git pull
git status --porcelain                  # must print nothing
git fetch origin main
git merge origin/main                   # resolve conflicts, then commit

2. Pick the version and survey the changes

Read the full file on GitHub · 184 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.

2d ago Changed · +1 lines 29e2638ab910
3d ago Changed · +18 lines · +22 tokens per session 0b3000fbb256
2mo ago First seen · 165 lines · 42 tokens per session scan A 4a27fae8ec4d

Subscribe to this mod's changes

release is a skill published in the GitHub repository jaemk/mind (1 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 2,112 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.

Claude Code Git and workflow Releases agents ai-skills claude cli developer-tools

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.

AtomicBot-ai/atomic-agent · 48 tokens

ship

Release pipeline for already-done local work. Dispatches /ground-state pre-flight, runs the project test suite, drafts a commit message, pushes, and opens a PR with a structured verification summary. Use when local changes are ready to hand off to review — e.g. 'ship this', 'push and open a PR', 'release this work'.…

griffinwork40/agent-afk · 93 tokens

afk-release

Cut a manual agent-afk release end to end. Auto-release was removed in #4146, so merging to main publishes nothing. This skill runs the read-only preflight (clean main equal to origin/main, CI green on that exact SHA, no publish in flight, npm in sync with the last tag), picks the semver bump from conventional commits…

griffinwork40/agent-afk · 156 tokens

mind: Skill for Claude Code