Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/blaisemoses01/playback-mcp/prnpx skills add BlaiseMoses01/playback-mcp --skill prgit clone --depth 1 https://github.com/BlaiseMoses01/playback-mcpWrote 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/skills/blaisemoses01/playback-mcp/pr)<a href="https://agentmods.dev/skills/blaisemoses01/playback-mcp/pr"><img src="https://agentmods.dev/badge/skills/blaisemoses01/playback-mcp/pr.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.00554 |
| Opus 5 | $0.00019 | $0.00277 |
| Sonnet 5 | $0.00008 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00055 |
Grade A, and why
pr 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 6d 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.
What it actually says
Opening a PR (playback-mcp)
This repo works on dev day-to-day; main is the release branch. PRs go dev → main.
1. Run the local CI gate first
From the repo root, before opening the PR:
pnpm run lint
pnpm run format:check
pnpm run typecheck
pnpm run build
pnpm test
Run pnpm run smoke too if the change touched the server's MCP protocol or tool surface
(server/src/tools/, bridge.ts, extension/src/content.ts). Note in the PR body if it
wasn't run (e.g. port 8765 already held by a live session) and why.
Fix anything red before opening the PR — don't rely on CI to catch it first.
2. Draft the PR body from the template
Use .github/pull_request_template.md's structure (Summary / Changes / Type of change /
Testing / Checklist). Write it to a scratch file, then pass with --body-file — heredocs
in --body mangle markdown checkboxes.
- Summary: why, in 1-3 sentences.
- Changes: bullet the actual diff, grouped by concern (features, docs, unrelated fixups if any snuck in from the branch).
- Testing: which of the gate commands above were run, and note anything skipped.
- Checklist: check off what's actually true — don't rubber-stamp.
3. Open it
gh pr create --repo BlaiseMoses01/playback-mcp --base main --head dev \
--title "<type>: <short summary>" \
--body-file /path/to/pr-body.md
4. Check CI, then merge
gh pr checks <number>
Wait for the required checks (quality, audit, CodeQL, Secret Scanning) to go green.
This repo merges with a real merge commit (see git log --merges, e.g. e608bdf Merge pull request #11 from ...) — not squash, not rebase:
gh pr merge <number> --merge
Confirm with the user before merging — it's the point where dev's changes actually
land on the release branch.
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.
- 6d ago First seen · 65 lines · 39 tokens per session scan A cb0806c2ea1f
pr is a skill published in the GitHub repository BlaiseMoses01/playback-mcp (5 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 554 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 2026-08-31.
Other skills, from other repositories
bump-version
Bump package versions across all platform packages and plugins in lockstep. Use when the user wants to bump versions, update versions, or prepare a release. Triggers on: bump version, bump versions, version bump, update version, prepare release.
release-tag
Cut a release by determining the SemVer bump from history, updating version files across any stack, refreshing the changelog, creating an annotated (optionally signed) Git tag, and pushing the release safely after pre-flight checks. Use when tagging a version, bumping the version, or preparing a release.
changelog
Generate a changelog or release notes from Git history, grouped by change type, written in user-facing language, with issue/PR links and breaking changes called out. Conventional-Commits aware and Keep a Changelog formatted; respects any existing CHANGELOG or tooling. Use when preparing release notes or updating…
release-packaging-checklist
Create and verify release artifacts for this extension using the existing build pipeline. Use when bumping versions, generating zip/crx files, computing checksums, and checking release consistency.
version-bump-and-changelog
Perform safe extension version bumps and changelog updates for this repository. Use when preparing a release, synchronizing version metadata, updating changelog entries, and validating generated artifacts.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.