playback-mcp: Skill for Claude Code

.claude/skills/release/SKILL.md

release is a skill for Claude Code from BlaiseMoses01/playback-mcp. It costs 41 tokens per session (854 once invoked), scanned A, original, MIT.

A release procedure for playback-mcp, a project published partly as an npm package and partly as a browser-extension archive. It defines how to change the version, update the changelog, merge the release, create a GitHub Release, and publish through CI.

In plain words
What is it for?
Use it when preparing a playback-mcp version: choose a semantic version, update the required package and extension files, merge the changes, tag or publish a GitHub Release, and trigger npm publication through the documented workflow.
Why use it?
It removes guesswork from releasing and helps keep the server package and browser extension on the same version. CI, or automated checks and publishing, performs the final publication after the release is created.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is BlaiseMoses01/playback-mcp's own configuration. It tells Claude Code how to work on playback-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 playback-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to BlaiseMoses01/playback-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/BlaiseMoses01/playback-mcp/main/.claude/skills/release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/BlaiseMoses01/playback-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/blaisemoses01/playback-mcp/release/github.svg)](https://agentmods.dev/skills/blaisemoses01/playback-mcp/release)
Your own site
<a href="https://agentmods.dev/skills/blaisemoses01/playback-mcp/release"><img src="https://agentmods.dev/badge/skills/blaisemoses01/playback-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/blaisemoses01/playback-mcp/release"><img src="https://agentmods.dev/badge/skills/blaisemoses01/playback-mcp/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 854 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 $0.00041 $0.00854
Opus 5.5 $0.00016 $0.00342
Sonnet 5.5 $0.00008 $0.00171
Haiku 4.5 $0.00004 $0.00085

Measured 2mo ago against content hash 689fa24e5f03, 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 2mo 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 · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing playback-mcp

Only server/ is published to npm (as playback-mcp); the extension is built and attached to the GitHub Release as a zip. .github/workflows/publish.yml does the actual publishing — it triggers on a published GitHub Release and expects the version to already be bumped and merged into main beforehand.

Full narrative version of this lives in CONTRIBUTING.md's "Releasing" section — keep both in sync if the process changes.

1. Pick the version

Semver. This project is pre-1.0, so treat it like 0.y.z: backwards-compatible additions bump the minor (0.1.0 → 0.2.0), fixes bump the patch.

2. Prep the release commit on dev

  • Bump the version in the two places it's declared (grep the old version string to confirm none were missed):

    • "version" in server/package.json
    • "version" in extension/manifest.json (what chrome://extensions shows)

    The McpServer version reported over MCP is no longer hardcoded — server/src/index.ts reads pkg.version at startup, so it tracks server/package.json automatically. And pnpm-lock.yaml doesn't record the workspace package's own version, so there's no lockfile step: pnpm install --frozen-lockfile still passes after a bump.

  • In CHANGELOG.md: rename ## [Unreleased] to ## [X.Y.Z] - YYYY-MM-DD, add a fresh empty ## [Unreleased] above it, and update the link refs at the bottom:

    [Unreleased]: https://github.com/BlaiseMoses01/playback-mcp/compare/vX.Y.Z...HEAD
    [X.Y.Z]: https://github.com/BlaiseMoses01/playback-mcp/releases/tag/vX.Y.Z
    
  • Run the full gate: pnpm run lint && pnpm run format:check && pnpm run typecheck && pnpm run build && pnpm test.

  • Commit as release: playback-mcp vX.Y.Z (see 9a1ca94, 07ed42a for precedent).

  • git push origin dev.

3. PR dev into main

Use the pr skill. Wait for CI to go green, confirm with the user, then merge with gh pr merge <number> --merge.

4. Tag and publish

From main, after the merge:

Read the full file on GitHub · 74 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. 2mo ago First seen · 74 lines · 41 tokens per session scan A 689fa24e5f03

Subscribe to this mod's changes

release is a skill published in the GitHub repository BlaiseMoses01/playback-mcp (5 stars, last pushed 23d ago), licensed MIT. It adds 41 tokens to every session and 854 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

release compared with skills from other repositories

release next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
releaseBlaiseMoses01/playback-mcpSkill523d agoMITA41Claude Code
changelogKhaledSaeed18/dotclaudeSkill5yesterdayMITA67Claude Code
release-tagKhaledSaeed18/dotclaudeSkill5yesterdayMITA64Claude Code
release-announcementpaperclipai/paperclipSkill111kyesterdayMITA42Claude Code, Codex
releasethedotmack/claude-memSkill114kyesterdayApache-2.0A13Claude Code
release-notesphuryn/pm-skillsSkill28k8d agoMITA57Claude Code
multi-agent-release-managerchromium/chromiumSkill25kyesterdayBSD-3-ClauseA27Claude Code, Codex