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-development/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-development)<a href="https://agentmods.dev/skills/getmcpm/cli/mcpm-development"><img src="https://agentmods.dev/badge/skills/getmcpm/cli/mcpm-development/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-development"><img src="https://agentmods.dev/badge/skills/getmcpm/cli/mcpm-development.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 | $0.00051 | $0.01143 |
| Opus 5.5 | $0.00020 | $0.00457 |
| Sonnet 5.5 | $0.00010 | $0.00229 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
mcpm-development 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcpm development
Read AGENTS.md, CONTRIBUTING.md and the relevant maintainer references. Work from the repo root. Honor existing authorization and complete the requested scope; this skill does not grant merge, tag, publication, deployment or unrelated changes.
Build the smallest complete change
- Check branch/base and dirty state. Read the touched implementation and callers, contracts, fixtures and scripts; identify what the user-visible change reaches. Preserve unrelated work; isolate conflicting work in a fresh checkout.
- For a bug, add a failing regression through the shared/public path before fixing the root cause. For new behavior, test its outcome and failure/coverage boundary. Keep changes surgical; reuse existing helpers. Pure docs changes need link/content/frontmatter checks rather than invented runtime tests.
- Use a supported Node and pnpm 10 with
pnpm install --frozen-lockfilewhen dependencies are needed. Preserve the tracked placeholder version, overrides and pinned baselines. Run focused tests, then the applicable checks below.
Select checks for the surface
| Changed surface | Appropriate verification |
|---|---|
| Docs/instructions/skills only | Check current commands/claims, links/import targets, skill frontmatter and distribution boundaries. For loading claims, use an isolated read-only host smoke and name its limits. |
| Runtime/CLI/config/stack | Regression and affected caller tests; pnpm run typecheck, pnpm run build, pnpm test. Check built public commands with synthetic homes and preserve unrelated config/secret/disabled/wrapper state. |
| Dependencies/package/build | Above plus pnpm dogfood:release (packs, clean-installs and smokes the binary). Preserve engines and all nine overrides; source tests alone cannot prove packaged dependency loading. |
| Coverage gates | pnpm run test:coverage and bash scripts/probe-coverage-thresholds.sh; a startup crash is not proof the negative threshold gate worked. |
| MCP/serve/relay/Skills/wire outputs | Relevant regressions plus pnpm run build, then a fresh pnpm pack --pack-destination <temporary-directory> and bash scripts/dogfood-protocol.sh <fresh-evidence-directory> <candidate.tgz>; read the protocol/serve/Skills/doctor docs for the affected modern/legacy direct/guarded paths. Run applicable harness self-checks. |
| Native client configuration/launch/consent | Follow the named native/Cursor/Gemini doc and explicit candidate mode. For native tooling, run its self-checks (node --test scripts/native-client/self-check.mjs and doctor checks when relevant). Real native proof needs pinned clients and disposable profiles/VMs. |
| macOS confinement | pnpm dogfood:confine on macOS plus relevant regression tests; state other platform/backend limitations. |
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 · 75 lines · 51 tokens per session scan A a41ce89e7bd0
mcpm-development is a skill published in the GitHub repository getmcpm/cli (3 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 1,143 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-development compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcpm-developmentgetmcpm/cli | Skill | 3 | yesterday | MIT | A | 51 | Claude Code, Codex |
| memorix-git-memoryAVIDS2/memorix | Skill | 906 | yesterday | Apache-2.0 | A | 31 | Claude Code |
| 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 |
| coding-agents-farmgriddynamics/rosetta | Skill | 370 | yesterday | Apache-2.0 | B | 32 | Claude Code |
| prepare-releasesampleXbro/agentsmesh | Skill | 27 | yesterday | MIT | A | 153 | Claude Code, Codex |
| release-managersampleXbro/agentsmesh | Skill | 27 | yesterday | MIT | A | 5 | Claude Code, Codex |