i18n-mcp: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from robin-heat/i18n-mcp. It costs 36 tokens per session (753 once invoked), scanned A, original, MIT.

A release checklist for publishing the @robinheat/i18n-mcp package to npm, including versioning, Git commits, tags, and pushing to the main branch.

In plain words
What is it for?
Use it to check tests and builds, commit pending work, bump the package version, create a release tag, and push the release to Git.
Why use it?
It reduces the risk of releasing from an untested or incorrectly committed state. It also makes the required release steps and the user's final publishing step clear.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; mentions Claude Code.

This is robin-heat/i18n-mcp's own configuration. It tells Claude Code how to work on i18n-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything i18n-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to robin-heat/i18n-mcp. 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/robin-heat/i18n-mcp/main/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/robin-heat/i18n-mcp

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.

agentmods badge for release

README.md
[![agentmods](https://agentmods.dev/badge/skills/robin-heat/i18n-mcp/release/github.svg)](https://agentmods.dev/skills/robin-heat/i18n-mcp/release)
Your own site
<a href="https://agentmods.dev/skills/robin-heat/i18n-mcp/release"><img src="https://agentmods.dev/badge/skills/robin-heat/i18n-mcp/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.

agentmods 80×15 button for release

Your own site · 80×15
<a href="https://agentmods.dev/skills/robin-heat/i18n-mcp/release"><img src="https://agentmods.dev/badge/skills/robin-heat/i18n-mcp/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 753 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.
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 5.1 $0.00036 $0.00753
Opus 5 $0.00018 $0.00377
Sonnet 5 $0.00007 $0.00151
Haiku 4.5 $0.00004 $0.00075

Measured 9d ago against content hash 690b0548b634, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, 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 9d 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 · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release @robinheat/i18n-mcp

Releases go straight to main — that is the established convention here (see the chore: release … commits in the log). Do not open a branch or a PR for a release.

1. Pre-flight

npm test          # must be green — do not release on a failing suite
npm run build
git status --short

If the working tree has uncommitted work, commit that first, as its own feat: / fix: commit with a descriptive body. The release commit must touch only package.json and package-lock.json.

Note on dist/: it is gitignored, but a handful of dist/ files are tracked from before the ignore was added. Feature commits here have historically included the rebuilt tracked dist/ files (git add -f). If you add a new module under src/, force-add its dist/ output too, or the committed build will import a file that is not in git.

2. Bump and tag

npm version patch -m "chore: release %s"    # or minor / major

This edits package.json, commits, and creates a vX.Y.Z tag in one step. Match the existing message format exactly.

3. Push

git push origin main --follow-tags

4. Publish — this step is the user's to run

Do not run npm publish yourself. It will fail. The npm account has 2FA required on writes; npm's web authorization flow prints an npmjs.com/auth/cli/... link and then waits for the user to approve it in a browser, and it only offers that prompt when stdin and stdout are a TTY. Anything that pipes output — the Bash tool, the ! prefix in the Claude Code prompt, a subagent — skips the prompt and fails with:

npm error code EOTP
npm error This operation requires a one-time password from your authenticator.

That error is misleading. Alex does not use an authenticator app, so --otp=<code> is not available, and --auth-type=web changes nothing (it is already npm 10's default and only affects npm login).

Ask the user to run this in a real terminal window, outside Claude Code:

Read the full file on GitHub · 82 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. 9d ago First seen · 82 lines · 36 tokens per session scan A 690b0548b634

Subscribe to this mod's changes

release is a skill published in the GitHub repository robin-heat/i18n-mcp (1 stars, last pushed 12d ago), licensed MIT. It adds 36 tokens to every session and 753 once invoked, about $0.0002 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 2026-09-04.