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.
git clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-SkillsWrote 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/plugins/stefanoskarakasis/product-marketing-skills/pmm-meta)<a href="https://agentmods.dev/plugins/stefanoskarakasis/product-marketing-skills/pmm-meta"><img src="https://agentmods.dev/badge/plugins/stefanoskarakasis/product-marketing-skills/pmm-meta/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/plugins/stefanoskarakasis/product-marketing-skills/pmm-meta"><img src="https://agentmods.dev/badge/plugins/stefanoskarakasis/product-marketing-skills/pmm-meta.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pmm-meta 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.
What it actually says
{
"name": "pmm-meta",
"displayName": "PMM Meta",
"description": "Meta skills that operate on the skill system itself: skill review, session learning, cross-skill synthesis and output verification.",
"version": "1.16.0",
"author": {
"name": "Stefanos Karakasis",
"url": "https://stefanoskarakasis.substack.com"
},
"homepage": "https://github.com/stefanoskarakasis/Product-Marketing-Skills/tree/main/pmm-meta",
"repository": "https://github.com/stefanoskarakasis/Product-Marketing-Skills",
"license": "MIT",
"skills": "./skills",
"keywords": [
"meta",
"skill quality",
"evals",
"pmm"
]
}
What it installs
The manifest is a name and a version. 4 skills, 4 commands travel with it, and installing the plugin installs all of them — 399 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 Changed ed0bc7fcdc8c
- 2d ago Changed · +1 lines 322dc0444bc1
- 6d ago Changed · +6 lines e2bda31770b6
- 8d ago Changed 2627e62cf9cf
- 12d ago Changed 3a9b55d2ac52
- 16d ago Changed 70e203a3d992
- 17d ago Changed c3cc15831435
- 21d ago Changed · +1 lines 5a65e2234d01
- 1mo ago Changed d868e6cf0c5a
- 1mo ago First seen · 13 lines scan A 52e69388e6fd
pmm-meta is a plugin published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
smk marketplace
Plugin marketplace listing 13 plugins: cursor-delegate, spring-clean, portal-skills, readable, decode.
cursor-delegate
Delegate self-contained coding/research tasks to the Cursor CLI (cursor-agent) from inside Claude Code, so they run on the Cursor subscription's quota instead of Claude's. One task via the cursor-delegate skill, or a whole fleet via cursor-orchestrate (Claude plans and reviews, Cursor executes in parallel). Workers…
readable
Beautiful replies as styled cards (Persian/RTL always, English by default): the model sends content only, the template carries all styling. KPI grids, charts, trend sparklines, timelines, flows, callouts, badges, CTA buttons, content cards, side-by-side columns, quotes, section numbering and section breaks, a minimal…
spring-clean
Two passes over a repo. spring-clean measures against a declared scoreboard, deletes or gitignores what does not belong, relocates dev docs, notes, clones and dumps to a -workspace repo, splits oversized files, draws package boundaries and writes its plan to a numbered unit list that survives a dead context. w.
learnable
Learn any subject properly, in courses you actually finish. Four commands: learn is the way in and the way back, new-course researches a whole domain with a fleet of agents and turns it into a taxonomy and a plan aimed at your real gaps, self-assess measures your true level with a scenario quiz that cannot be gamed…
getpix
Search free stock-image sources (Pexels, Pixabay, Unsplash, Openverse, Wikimedia), show photos right in the chat, or drop optimized WebP images into your project with alt text and attribution. Includes photo-pass: a whole-site art-direction pass.