Borrowing it
Nothing to install: this file belongs to getmcpm/cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/getmcpm/cli/main/.agents/skills/mcpm-release/SKILL.mdgit clone --depth 1 https://github.com/getmcpm/cliWrote 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/getmcpm/cli/mcpm-release)<a href="https://agentmods.dev/skills/getmcpm/cli/mcpm-release"><img src="https://agentmods.dev/badge/skills/getmcpm/cli/mcpm-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.
<a href="https://agentmods.dev/skills/getmcpm/cli/mcpm-release"><img src="https://agentmods.dev/badge/skills/getmcpm/cli/mcpm-release.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00052 | $0.01784 |
| Opus 5.5 | $0.00021 | $0.00714 |
| Sonnet 5.5 | $0.00010 | $0.00357 |
| Haiku 4.5 | $0.00005 | $0.00178 |
Grade A, and why
mcpm-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcpm release
Read the repo AGENTS.md, CONTRIBUTING.md and maintainer context first. Run commands from the relevant repository root; use its current scripts and frozen toolchain. The canonical source of this workflow is this repo file, not a same-name global skill. Do not modify global skills/config as part of a release.
A getmcpm release includes checking and updating its companion repositories. Publishing the CLI alone is not a fully synchronized release. Audit companions before tagging; finalize their updates after the published artifact is available.
Scope and authorization
- Include companion inspection, scoped synchronization changes, validation and reviewable PRs in the release workflow. Respect explicit repository exclusions.
- Use existing authorization without asking again. A CLI release instruction does not by itself authorize merging or deploying other repositories. Complete the concrete companion changes and checks before requesting any missing final approval; report pending merges/deployments honestly.
- This skill is not authorization to publish, merge unrelated PRs, deploy a site or contact contributors. Follow the user's requested builder/reviewer workflow.
- Preserve dirty worktrees and active branches; use isolated release checkouts. Read each repository's instructions and current release/update scripts.
Before the tag: inspect the whole release surface
Check live default branches, the latest published CLI and open PRs. Do not rely on a past release's pins, score table or prior assertion that companions are synced.
| Repository | Required audit |
|---|---|
| getmcpm/cli | Intended merged scope, release source, CI, changelog, docs and public mcpm skill |
| getmcpm/guard-playground | CLI dependency/lock, engine.lock.json, generated browser engine/metadata, corpus pin, pending updates and deployment state |
| getmcpm/mcp-guardbench | Adapter compatibility, pinned published-version results, README scoreboard, corpus commit and pending fixes |
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.
- yesterday First seen · 145 lines · 52 tokens per session scan A b57b951426f8
mcpm-release is a skill published in the GitHub repository getmcpm/cli (3 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,784 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 2026-11-06.
mcpm-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcpm-releasegetmcpm/cli | Skill | 3 | yesterday | MIT | A | 52 | Claude Code, Codex |
| changelog-generatorMoizIbnYousaf/Ai-Agent-Skills | Skill | 1.2k | 1mo ago | MIT | A | 48 | Claude Code, Codex |
| share-a-libraryMoizIbnYousaf/Ai-Agent-Skills | Skill | 1.2k | 1mo ago | MIT | A | 41 | Claude Code, Codex |
| prepare-releasesampleXbro/agentsmesh | Skill | 27 | yesterday | MIT | A | 153 | Claude Code, Codex |
| release-managersampleXbro/agentsmesh | Skill | 27 | yesterday | MIT | A | 5 | Claude Code, Codex |
| package-release-engineeringsampleXbro/agentsmesh | Skill | 27 | yesterday | MIT | A | 38 | Claude Code, Codex |
| homebrew-packagingsampleXbro/agentsmesh | Skill | 27 | yesterday | MIT | A | 37 | Claude Code, Codex |