A release procedure for shipping a new Houston software version. It uses semantic versioning, a numbering system where version changes describe the size of a release.

Use it to make the default patch version change, write release notes when needed, commit and tag the release, push it, and let CI build, sign, and notarize it.

It keeps package versions consistent and stops the process at a draft release so the user can publish it manually.

release — Skill for Claude Code and Codex by gethouston/houston

Install

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.

Clone the repo

git clone --depth 1 https://github.com/gethouston/houston

agentmods

npx agentmods add skills/gethouston/houston/release

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.

README.md

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

Your own site

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

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,358 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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	$0.00046	$0.01358
Opus 5.5	$0.00018	$0.00543
Sonnet 5.5	$0.00009	$0.00272
Haiku 4.5	$0.00005	$0.00136

Measured 1mo ago against content hash 73ae62052cb6, 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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

release — 91% identical, 27 lines differ

skills/release/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/release

Version. Bump. Tag. Push. Done.

Versioning

All packages share ONE version. Every release bumps ALL.

Semver 0.x.y
Default: patch bump (0.3.0 → 0.3.1). Do this always unless told otherwise.
Minor bump (0.3.x → 0.4.0) needs explicit user permission. Never bump minor on own. Suggest: "This might warrant 0.4.0 — want minor?" Wait for approval.
No rush to 1.0. FastAPI was 0.x for years in prod. Same energy.

Standard flow (CI/CD)

./scripts/version.sh 0.3.X          # bump all package.json + Cargo.toml

# REQUIRED for any user-visible release: write the notes file BEFORE
# tagging. CI reads `.github/release-notes/<version>.md` verbatim and
# uses it as the GitHub release body. Skip only for trivial hotfixes
# (CI then auto-generates from conventional-commit subjects, which is
# weak signal for end users). See `.github/release-notes/README.md`
# for what good notes look like + an example at `.../0.4.0.md`.
$EDITOR .github/release-notes/0.3.X.md

git add -A && git commit -m "release: v0.3.X"
git tag v0.3.X
git push origin main --tags

GH Actions (.github/workflows/release.yml) takes over:

Builds houston-engine for BOTH aarch64-apple-darwin AND x86_64-apple-darwin
Builds Tauri app w/ --target universal-apple-darwin (one fat .app)
Signs w/ Apple Developer ID ($APPLE_SIGNING_IDENTITY)
Notarizes .app w/ Apple
Creates signed .dmg
Verifies engine sidecar is lipo'd fat (arm64 + x86_64 both present)
Generates latest.json w/ darwin-aarch64* AND darwin-x86_64* keys
Creates draft GH Release w/ all artifacts

One DMG covers Apple Silicon + Intel (macOS Universal; the lipo/verify steps live in .github/workflows/release.yml).

Duration: ~15-20 min (2-arch compile).

After CI: the release stays as a draft. Stop there. The user reviews the draft and clicks "Publish" themselves. Do NOT run gh release edit --draft=false or otherwise auto-publish — publishing is the user's call, every time.

Read the full file on GitHub · 97 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.

1mo ago First seen · 97 lines · 46 tokens per session scan A 73ae62052cb6

Subscribe to this mod's changes

release is a skill published in the GitHub repository gethouston/houston (119 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,358 once invoked, about $0.0002 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 2026-08-30.

CI and CD DevOps and cloud Git and workflow Releases

github-release-management

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.

ruvnet/RuView · 27 tokens

agent-github-modes

Agent skill for github-modes - invoke with $agent-github-modes.

ruvnet/ruflo · 21 tokens

factory-ship

Experimental workflow for publishing and completing configured software delivery work. Use when the user or an enabled factory policy asks to ship.

BuilderIO/skills · 28 tokens

releasepr

Adopt, configure, run, or troubleshoot compozy/releasepr in a consuming repository, including Actions, beta/stable/legacy plans, notes, dry-runs, and publication. Excludes pr-release internals and general versioning advice.

compozy/compozy · 53 tokens

gitlab-devops

GitLab DevOps operations — issues, merge requests, CI/CD pipelines, repository browsing, labels, milestones, releases, and wiki management. Use when querying GitLab project status, monitoring pipeline executions, browsing repository files, creating issues for network findings, opening merge requests for config…

automateyournetwork/netclaw · 67 tokens

seed-snapshot-release

An automated workflow for creating and tracking a snapshot release of the pull request on the current branch. A snapshot release is a temporary package build used for testing a branch before a normal release.

daangn/seed-design · 19 tokens