A repository release procedure for the MultiClaude project. It supports draft-first releases to targets such as beta, main, the current branch, or another named branch.

It helps preview a release, check the working tree and GitHub access, choose stable or prerelease status, confirm a version, and execute the release.

It checks release prerequisites before publishing and stops when authentication, duplicate tags, duplicate releases, or uncommitted changes could cause problems.

How nguyennguyenit/MultiClaude configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nguyennguyenit/MultiClaude. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nguyennguyenit/MultiClaude/master/.claude/skills/release/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/nguyennguyenit/MultiClaude

Made for: Claude Code.

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/nguyennguyenit/multiclaude/release.svg)](https://agentmods.dev/skills/nguyennguyenit/multiclaude/release)

Your own site

<a href="https://agentmods.dev/skills/nguyennguyenit/multiclaude/release"><img src="https://agentmods.dev/badge/skills/nguyennguyenit/multiclaude/release.svg" alt="Measured on agentmods" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 656 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	$0.00028	$0.00656
Opus 5	$0.00014	$0.00328
Sonnet 5	$0.00006	$0.00131
Haiku 4.5	$0.00003	$0.00066

Measured 8d ago against content hash 69c14db2666a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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/skills/release/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MultiClaude Release

Use this skill only inside the MultiClaude repo.

Command grammar:

/release <target>

Valid targets:

current
main
beta
any real branch name

Workflow

Run preview first:

node "$(git rev-parse --show-toplevel)/scripts/release/release-command.mjs" preview \
  --target <target>

Parse the JSON response.
Stop immediately if:
- preflight.ghAuthValid is false
- preflight.duplicateTag is true
- preflight.duplicateRelease is true
If preflight.cleanTree is false, tell the user the working tree is dirty and ask whether they want to commit the current changes before release.
- If yes, help them commit first, then rerun preview.
- If no, stop without executing the release.
Ask only for values the preview says are still missing:
- if requiresReleaseTypePrompt, ask whether the release is stable or prerelease
- if requiresVersionPrompt, offer suggestedVersion when present and ask the user to confirm or replace it
Re-run preview with the chosen --release-type and --version before execution:

node "$(git rev-parse --show-toplevel)/scripts/release/release-command.mjs" preview \
  --target <target> \
  --release-type <stable|prerelease> \
  --version <version>

If the refreshed preview says requiresBranchSwitch is true, tell the user which branch the command will switch to before execution.
If the refreshed preview says requiresCustomStableConfirm is true, ask for one extra explicit confirmation.
Show the final execution summary:
- target
- resolved branch
- version
- release type
- whether the command will switch branches
Only after the user confirms, run execute:

node "$(git rev-parse --show-toplevel)/scripts/release/release-command.mjs" execute \
  --target <target> \
  --version <version> \
  --release-type <stable|prerelease> \
  --confirm

Add --confirm-custom-stable when the refreshed preview flagged requiresCustomStableConfirm.
Report the returned draft release URL, workflow run URL, asset summary, and any branchPushWarning. Stop at draft-ready. Do not publish the GitHub release.

Read the full file on GitHub · 81 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.

8d ago First seen · 81 lines · 28 tokens per session scan A 69c14db2666a

Subscribe to this mod's changes

release is a skill published in the GitHub repository nguyennguyenit/MultiClaude (22 stars, last pushed 27d ago), licensed MIT. It adds 28 tokens to every session and 656 once invoked, about $0.0001 per session on Opus 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.

Git and workflow Releases

release-announcement

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

paperclipai/paperclip · 42 tokens

multi-agent-release-manager

Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.

chromium/chromium · 27 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens

pack-submit

Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.

aeonfun/aeon · 27 tokens

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 tokens

updater_guide

Guidance for checking for and installing Row-Bot updates.

siddsachar/row-bot · 17 tokens

MultiClaude: Skill for Claude Code