release

A release procedure for a software project: it finds the previous version, reviews commits, increments the package version, creates a tag, pushes the changes, waits for the build, and publishes release notes.

In plain words
What is it for?
Use it to prepare a new project release, summarize user-facing changes by category, monitor GitHub Actions, and publish the resulting draft release.
Why use it?
It turns several release steps into one documented sequence and helps keep the version, repository, build, and release page aligned.

Command for Claude Code

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 commands/doctly/switchboard/release
Clone the repo
git clone --depth 1 https://github.com/doctly/switchboard

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 482 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00482
Opus 5 $0.00000 $0.00241
Sonnet 5 $0.00000 $0.00096
Haiku 4.5 $0.00000 $0.00048

Measured 2d ago against content hash fc8c738d134a, 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 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/commands/release.md · 38 lines

What it actually says

Perform a release for this project. Steps:

  1. Find the most recent version tag with git describe --tags --abbrev=0 and collect all commits between it and HEAD using git log {prev_tag}..HEAD --format="%B---"
  2. Bump the version with npm version patch --no-git-tag-version
  3. Commit the version bump with message: v{version}: {short summary of changes}
  4. Create a git tag v{version}
  5. Push commits and tag: git push && git push --tags
  6. Wait for the GitHub Actions build to complete using gh run watch on the latest run
  7. Once the build finishes and creates a draft release, publish it with release notes using gh release edit v{version} --draft=false --notes "..."
  8. Release notes format:
    ## What's Changed
    
    ### {Category}
    - {change description}
    
    ### {Category}
    - {change description}
    
    Group changes by category (e.g. "Features", "Bug Fixes", "Performance Improvements", etc.).

Writing the release notes

Write them for the person using the app, not for someone reading the git log. Read every commit between the tags so nothing user-facing gets missed — but the notes describe what changed for the user, they are not a summary of each commit.

Each entry says what the user will notice: what the app did before, what it does now. Don't name internal symbols, columns, migrations, or files.

Leave out:

  • Fixes for bugs introduced after the previous tag. The user never ran that code, so there's nothing to announce. Describe only the net change since the last release.
  • Refactors, schema migrations, test-only changes, and dev tooling with no visible effect.
  • Cosmetic tweaks too small to notice — padding, font sizes, color nudges.
  • Anything not confirmed to actually work. If a change is unverified or known broken, raise it before publishing instead of listing it.

Collapse a feature and its follow-up fixes into a single entry describing where things landed. Several commits often add up to one user-facing change; one commit sometimes makes several.

A short release with three real entries beats a padded one with twelve. If nothing user-facing changed, say so plainly.

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 · 38 lines · 0 tokens per session scan A fc8c738d134a

Subscribe to this mod's changes

release is a command published in the GitHub repository doctly/switchboard (329 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 482 tokens. 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.