mal-mcp: Skill for Claude Code

.agents/skills/release/SKILL.md

release is a skill for Claude Code, Codex from Grinv/mal-mcp. It costs 46 tokens per session (1,713 once invoked), scanned A, original, MIT.

A release workflow for the mal-mcp package, which connects agents to MyAnimeList. It prepares release notes, checks that package files agree, and publishes a new version.

In plain words
What is it for?
Use it when cutting, publishing, or tagging a new mal-mcp version.
Why use it?
It reduces mistakes when releasing a package, such as mismatched version numbers, incomplete documentation, or an unsafe Git tag.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is Grinv/mal-mcp's own configuration. It tells Claude Code and Codex how to work on mal-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 mal-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Grinv/mal-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/Grinv/mal-mcp/main/.agents/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Grinv/mal-mcp

Made for: Claude Code, Codex.

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/grinv/mal-mcp/release/github.svg)](https://agentmods.dev/skills/grinv/mal-mcp/release)
Your own site
<a href="https://agentmods.dev/skills/grinv/mal-mcp/release"><img src="https://agentmods.dev/badge/skills/grinv/mal-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/grinv/mal-mcp/release"><img src="https://agentmods.dev/badge/skills/grinv/mal-mcp/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,713 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 $0.00046 $0.01713
Opus 5.5 $0.00018 $0.00685
Sonnet 5.5 $0.00009 $0.00343
Haiku 4.5 $0.00005 $0.00171

Measured 1mo ago against content hash 5e4c32de92b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

.agents/skills/release/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing

package.json is the single source of truth for the version. The npm version lifecycle hook runs scripts/sync-version.mjs, which propagates it to src/version.ts, manifest.json, server.json (incl. the .mcpb release-asset URL), and CHANGELOG.md — it renames ## [Unreleased] to ## [<version>] - <date> and reopens a fresh, empty ## [Unreleased] above it, rolling the trailing compare-link block forward the same way; version.test.ts guards that the derived files never drift, and unit-tests the CHANGELOG rename directly (renderChangelogRelease). You do not need to rename the heading yourself — don't hand-edit it back to [Unreleased] after running npm version.

A preversion hook (scripts/preversion-check.mjs) runs first — it's a presence-only safety net, not a substitute for actually running the skill below as a real judgment step. It runs two checks, in order:

  • Unpushed-tag race: if the current package.json version already has a local git tag, it blocks unless that tag is also on origin — this is the exact race that once orphaned a version in a sibling repo (npm version run twice within minutes, the first tag/commit never pushed, silently buried under the second). Push the dangling tag (git push origin vX.Y.Z) or delete it if it was a mistake (git tag -d vX.Y.Z), then retry.
  • Empty changelog: it blocks npm version if CHANGELOG.md's [Unreleased] section is empty: run the changelog-style skill against the commits since the last tag first — it's what actually makes the entries short, self-describing, free of implementation detail, and linked to their commits; the hook only confirms something is there, not that it follows that style. (Or re-run with CONFIRM_EMPTY_CHANGELOG=1 if this release genuinely has no user-facing changes, e.g. a pure dependency bump.)

When invoked as this skill, run these as explicit steps, not optional — don't rely on the preversion hook alone to catch a skipped one:

  1. Invoke the changelog-style skill against the commits since the last tag; write/fix the [Unreleased] entries per its style rules (heading rename happens later, automatically — see above).
  2. Run the docs-consistency-check skill.
  3. Commit all of the above.
  4. npm version <patch|minor|major> — preversion gate, then bumps + syncs every file (including the CHANGELOG rename) + commits "release: vX.Y.Z"
    • tags vX.Y.Z.
  5. git push --follow-tags — pushing the tag triggers .github/workflows/release.yml. Verify the tag actually reached the remote: git ls-remote --tags origin | grep vX.Y.Z. --follow-tags only pushes annotated tags (npm version's default) reachable from what's being pushed — if you ever re-tag by hand (e.g. git tag -f vX.Y.Z <commit> to fix something before pushing), that recreates it as a lightweight tag, which --follow-tags silently skips; push it explicitly instead (git push origin vX.Y.Z) and re-verify with git ls-remote. (Confirmed live 2026-07-29: a git tag -f without -a produced exactly this silent no-op.)

The tag push (v*) runs the Release workflow: check:api gate → build → test → pack .mcpb → GitHub Release → npm publish (OIDC trusted publishing, with provenance — no token) → publish to the official MCP Registry (mcp-publisher, GitHub OIDC; the binary is pinned to an exact version + verified SHA-256 rather than latest). The workflow's CHANGELOG-extraction step fails loudly (not silently) if it can't find a ## [<version>] section, as a backstop if the heading rename above is somehow bypassed. The npm publish step is itself pinned to an exact verified-good npm version — no token — and is skipped without failing the job if this version is already on npm, so a re-run after a partial failure doesn't abort. The .mcpb SHA-256 injection into server.json likewise fails loudly if the injection didn't actually match a package, instead of silently leaving a stale hash. Never hand-edit the version in the derived files; bump package.json via npm version and let the hook sync the rest.

Read the full file on GitHub · 109 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. 1mo ago First seen · 109 lines · 46 tokens per session scan A 5e4c32de92b4

Subscribe to this mod's changes

release is a skill published in the GitHub repository Grinv/mal-mcp (3 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,713 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

release

Cut a release of steam-games-mcp — draft CHANGELOG entries, check docs/metadata consistency, then bump/tag/push. Use when asked to release, cut a version, or publish a new version of this package.

Grinv/steam-games-mcp · 47 tokens

changelog-style

Turn a commit range into CHANGELOG.md entries following common-changelog style. Use when finishing a PR (adding to the [Unreleased] section) or cutting a release (moving [Unreleased] under a new version heading).

Grinv/steam-games-mcp · 50 tokens

verify-cli

Run smoke tests against the mpak CLI to verify all commands work correctly before publishing a new release.

NimbleBrainInc/mpak · 23 tokens

git-wrapup

Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…

cyanheads/anime-mcp-server · 109 tokens

release-and-publish

Ship a release end-to-end across every registry the project targets (npm, MCP Registry, GitHub Releases for .mcpb bundles, GHCR). Runs the final verification gate, fast-forwards main when the release rode a release PR, creates the annotated tag on the commit main now points at, pushes commits and tags, then publishes…

cyanheads/anime-mcp-server · 155 tokens

release-pr-review

Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…

cyanheads/anime-mcp-server · 136 tokens