release

A release runbook for publishing a versioned bex CLI, including its tag, automated release workflow, and distribution checks.

In plain words
What is it for?
Checking the branch, working tree, remote state, CI results, and previous versions; then choosing a version, pushing its tag, watching the release, and verifying distribution channels.
Why use it?
It ensures releases come only from shipped, tested code and prevents reusing or moving public version tags.

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

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,088 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 $0.00072 $0.01088
Opus 5 $0.00036 $0.00544
Sonnet 5 $0.00014 $0.00218
Haiku 4.5 $0.00007 $0.00109

Measured 2d ago against content hash 7eef6e6326a6, 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 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.

Makes network callslowCapability

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

allowed-tools: Bash(git:*), Bash(gh:*), Bash(cosign:*), Bash(brew:*), Bash(scripts/install-bex.sh:*), Bash(curl:*), AskUserQuestion
.claude/skills/release/SKILL.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task: Release a bex component

/release <component> [patch|minor|major|X.Y.Z] — component today: cli (tag prefix bex-cli/v). platform is reserved for the ADR058 bex/v* train and must be rejected until that exists.

Invariant (ADR058): code flows into main only through /ship; versions exist only as tags minted here. This skill never commits, never touches the working tree, and never re-uses or moves an existing tag. A pushed tag is a public, immutable release.

Step 1 — Preconditions (all must hold; stop with a clear message otherwise)

  1. Working tree clean (git status --porcelain empty) and current branch main.
  2. HEAD == origin/main after git fetch origin main — releases are cut only from shipped code.
  3. CI for HEAD is green: gh run list --commit $(git rev-parse HEAD) shows no failed/in-progress required runs. If runs are still in progress, wait for them.

Step 2 — Determine the version

  1. Last tag: highest existing bex-cli/v* by semver (git tag -l 'bex-cli/v*'; also git fetch --tags first). No tags yet ⇒ this is the first release; default 0.1.0 unless an explicit version was given.
  2. List commits since that tag touching the component's paths — for cli: lego/cli/**, scripts/bex-cli-*, scripts/install-bex*, .github/workflows/cli-release.yml. If there are none, say so and stop (nothing to release) unless the user explicitly insists.
  3. Suggested bump from Conventional Commits over those commits: any !/BREAKING CHANGE → major (while on 0.x, propose minor instead and say why), else any feat → minor, else patch.
  4. If the user passed a level or exact version, that wins. Otherwise present the suggestion plus the commit list and ask for confirmation (AskUserQuestion) — the confirmed version is the authorization to publish.

Step 3 — Tag and push

git tag -a "bex-cli/vX.Y.Z" -m "bex CLI vX.Y.Z"
git push origin "bex-cli/vX.Y.Z"

Step 4 — Watch the release workflow to green

The tag triggers release (bex CLI) (cli-release.yml). Watch it like /ship watches deploys (gh run watch <id> --exit-status); rerun genuine infra flakes (max 2). If it fails on a real defect: do not delete or move the tag. Diagnose, report, get the fix landed via /ship, then cut the next patch version here. If the failure happened before the GitHub release was created, deleting the never-published tag is permitted with user confirmation.

Read the full file on GitHub · 50 lines

Files

What ships with it

1 file 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.

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. 2d ago First seen · 50 lines · 0 tokens per session scan A 7eef6e6326a6

Subscribe to this mod's changes

release is a skill published in the GitHub repository bex-co/bex (420 stars, last pushed 3d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,088 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

cut-release

Cut (publish) a release of meshery/meshery by publishing the current Release Drafter draft. Use this whenever the user asks to "cut a release", "publish the release", "ship a release", "release meshery", "do a release", "release the latest merge", or wants recently merged PRs to go out to users. Handles waiting for…

meshery/meshery · 137 tokens

gh-axi

Operate GitHub through the gh-axi CLI - issues, pull requests, workflow runs, workflows, releases, repositories, labels, Projects (v2), Actions secrets and variables, search, and raw API access. Use whenever a task touches GitHub: listing or filing issues, reviewing or merging PRs, checking CI runs, triggering…

meshery/meshery · 87 tokens

superplane-changelog

When generating a SuperPlane changelog from merged commits. Use for "what's new" summaries with new integrations, new components/triggers, improvements, security updates, and bug fixes. Output is user-focused markdown in tmp/.

superplanehq/superplane · 50 tokens

ship-release

Drive a Telepresence release from a prepared branch all the way through CI, docs, the Releases workflow, and PR merges. Assumes make prepare-release has already been run locally and the branch with that commit was pushed and a PR opened. Use when the user says "ship the release", or "complete the release". User-only.

telepresenceio/telepresence · 72 tokens

openspec-archive-change

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

fonoster/fonoster · 31 tokens

changelog-entry

Add a new entry to CHANGELOG.yml under the current unreleased version (or create the version block if needed), then regenerate documentation. Use when the user says things like "add a changelog entry", "log this fix in the changelog", or "/changelog-entry".

telepresenceio/telepresence · 60 tokens