release

A release command for the rem project that reviews changes, chooses a version number, runs tests, and prepares a new release. Version numbers follow semantic versioning, where changes indicate breaking updates, new features, or fixes.

In plain words
What is it for?
Use it to inspect commits since the last tag, classify the release, run the project’s tests, and create the next rem release.
Why use it?
It reduces guesswork when deciding whether a release needs a major, minor, or patch version. It also requires confirmation before proceeding with the proposed version.

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/bro3886/rem/release
Clone the repo
git clone --depth 1 https://github.com/BRO3886/rem

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 1,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.01004
Opus 5 $0.00000 $0.00502
Sonnet 5 $0.00000 $0.00201
Haiku 4.5 $0.00000 $0.00100

Measured 2d ago against content hash f317d8e5373a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

release scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://rem.sidv.dev/install | bash

Makes network callslowCapability

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

curl -fsSL https://rem.sidv.dev/install | bash
.claude/commands/release.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a new release for the rem project.

Step 1: Analyze Changes

Run these commands to understand what changed since the last release:

git tag --sort=-v:refname | head -1   # Latest tag
git log <latest-tag>..HEAD --oneline  # Commits since last release
git diff <latest-tag>..HEAD --stat    # Files changed

Read the commit messages carefully. Classify the release:

Semver Rules

  • MAJOR (vX.0.0): Breaking changes — removed commands, renamed flags, changed default behavior, dropped compatibility
  • MINOR (v0.X.0): New features, new commands, new flags, new packages. No breaking changes.
  • PATCH (v0.0.X): Bug fixes, docs-only changes, performance improvements, dependency bumps. No new features.

Look for commits prefixed with:

  • feat(...) → MINOR bump (or MAJOR if feat! or contains BREAKING CHANGE)
  • fix(...) → PATCH bump
  • docs(...), chore(...), refactor(...), perf(...) → PATCH bump
  • ! suffix or BREAKING CHANGE in body → MAJOR bump

If the current version is pre-1.0 (v0.x.y), breaking changes bump MINOR not MAJOR.

Present the proposed version to the user and ask for confirmation before proceeding.

Step 2: Run Tests

go test ./...

All tests must pass. Do not proceed if any test fails.

Step 3: Tag FIRST, Then Build

CRITICAL: The tag MUST be created BEFORE building. The Makefile uses git describe --tags to embed the version string in the binary. If you build before tagging, the binary will report the wrong version (e.g., v0.5.0-2-gae75da9 instead of v0.6.0).

git tag v<VERSION>
git push origin v<VERSION>

Step 4: Build Release Binaries

make release

This produces bin/rem-darwin-arm64.tar.gz and bin/rem-darwin-amd64.tar.gz.

Verify the version is correct before uploading:

cd /tmp && tar -xzf /path/to/bin/rem-darwin-arm64.tar.gz && ./rem version && rm ./rem

The output must show rem v<VERSION>, not a describe-style string like v0.X.Y-N-gHASH.

Read the full file on GitHub · 130 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. 2d ago First seen · 130 lines · 0 tokens per session scan C f317d8e5373a

Subscribe to this mod's changes

release is a command published in the GitHub repository BRO3886/rem (149 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,004 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.