Borrowing it
Nothing to install: this file belongs to Arclude/Arterm-CLI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Arclude/Arterm-CLI/main/.claude/commands/cut-release.mdgit clone --depth 1 https://github.com/Arclude/Arterm-CLIWrote 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.
[](https://agentmods.dev/commands/arclude/arterm-cli/cut-release)<a href="https://agentmods.dev/commands/arclude/arterm-cli/cut-release"><img src="https://agentmods.dev/badge/commands/arclude/arterm-cli/cut-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.
<a href="https://agentmods.dev/commands/arclude/arterm-cli/cut-release"><img src="https://agentmods.dev/badge/commands/arclude/arterm-cli/cut-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00022 | $0.01168 |
| Opus 5.5 | $0.00009 | $0.00467 |
| Sonnet 5.5 | $0.00004 | $0.00234 |
| Haiku 4.5 | $0.00002 | $0.00117 |
Grade A, and why
cut-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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut release $ARGUMENTS of arterm.
The changelog entry is the point of this command. scripts/generate_release_notes.sh
renders changelog/v<version>.json into the GitHub release body when it exists, and
silently falls back to raw commit subjects when it does not — which is how v0.9.0
through v0.10.3 shipped with contributor shorthand as their release notes. Do not
reach the tagging step without the entry written and validated.
1. Preconditions
Stop and report if any of these fail — do not "fix" them as part of the release:
- The version argument is present and looks like
vX.Y.Z. If it is missing, ask which version to cut; do not infer one. - The tag does not already exist locally or on origin (
git tag -l,git ls-remote --tags origin). - You are on
main, the working tree has no tracked modifications, andmainis level withorigin/main. - CI is green on the commit being released:
gh run list --branch main --limit 3. A red or in-progress run means stop and say so.
2. Read what the release contains
scripts/changelog_entry.py commits $ARGUMENTS
This lists every non-merge commit since the previous tag. Commits whose
conventional-commit prefix is internal (test, ci, chore, refactor, style,
build, gate) are marked [internal?] as a drafting hint — read them, do not
trust the mark blindly, and never filter silently.
Read the actual diffs where a subject is not self-explanatory. The commit log is the source of truth; the changelog is a user-facing layer over it.
3. Write changelog/v<version>.json
Follow the schema and writing guidelines in changelog/README.md. In short:
- Describe the effect on the user, not the implementation.
- One sentence per item.
highlightsholds only the 1-3 changes a user would actually notice. Everything else goes inimprovementsorfixes.- Omit empty arrays entirely. Omit
titleunless the release has an obvious theme. - Skip internal-only changes. If the whole release is internal, say so in a single
improvementsitem rather than padding the entry. versionis the number without the leadingv;dateis today inYYYY-MM-DD.
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 · 112 lines · 22 tokens per session scan A 1ebca2c11fe8
cut-release is a command published in the GitHub repository Arclude/Arterm-CLI (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,168 once invoked, about $0.0001 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.
Other commands, from other repositories
pr
A guided command for preparing a GitHub Pull Request, which is a proposed set of repository changes for review and merging. It reads the branch history and changed files to draft the request.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
branch
Show Claude Code costs per git branch / PR.
post-release.en
Read and execute the post-release skill from .agents/skills/post-release/SKILL.md.
release
Publish a release branch.
finish-branch-execute
Step 4 of finishing-a-development-branch: Execute chosen integration option (merge, PR, PR+dance, keep, or discard).