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/cmj-hub/claude-evpWrote 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/cmj-hub/claude-evp/claude-evp)<a href="https://agentmods.dev/plugins/cmj-hub/claude-evp/claude-evp"><img src="https://agentmods.dev/badge/plugins/cmj-hub/claude-evp/claude-evp/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/cmj-hub/claude-evp/claude-evp"><img src="https://agentmods.dev/badge/plugins/cmj-hub/claude-evp/claude-evp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
evp 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 4d 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
{
"name": "evp",
"version": "0.7.0",
"description": "An Early Value Proposition is a ≤22-word line matched to a Schwartz awareness tier. Same product, five lines, because the unaware buyer and the vendor-comparing buyer are not the same reader. Step 2 of the GTM operator suite.",
"author": {
"name": "JMC Go-to-Market Systems",
"url": "https://jaymountconsulting.com"
},
"homepage": "https://jaymountconsulting.com/skills",
"repository": "https://github.com/cmj-hub/claude-evp",
"license": "MIT",
"keywords": [
"evp",
"value-proposition",
"schwartz",
"awareness",
"positioning",
"b2b",
"copywriting"
],
"icon": ".claude-plugin/icon.png",
"documentationUrl": "https://github.com/cmj-hub/claude-evp#readme",
"supportUrl": "https://github.com/cmj-hub/claude-evp/issues"
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 133 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed cea3209f6a0a
- 17d ago Changed · +3 lines bacbbda53a47
- 19d ago Changed · +11 lines f3a8758e8f6c
- 1mo ago Changed · +2 lines d4751c6d0f7e
- 1mo ago First seen · 9 lines scan A 2a48987f6668
evp is a plugin published in the GitHub repository cmj-hub/claude-evp (3 stars, last pushed 4d ago), 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
psp
A Pain Signal Profile is a five-part buying brief: a public signal, the operational pain it implies, why that pain is acute now, who feels it at 11am on Tuesday, and the exact phrases that person uses. It replaces a static ICP. Step 1 of the GTM operator suite.
linkedin-engine
Run your entire LinkedIn motion inside Claude Code. 29 skills across content, warming and outreach, built from 7 source playbooks, a 13-tool LinkedIn MCP layer, and a 17-command CLI. Build authority with content, warm every target before you message them, and convert warm conversations to booked calls. A SessionStart…
b2b-marketing-skills
B2B product marketing skills for AI agents — customer research, positioning, messaging, launches, sales narratives, demos, customer proof, category POVs, and AI PMM review.
hormozi-gtm
Alex Hormozi-style GTM operation for LEVEL's team and clients. Offers, copy, ads, pricing, business plans, and diagnostics. Persona always on. Humanizer required on external copy.
marketing-os
An entire marketing department as one Claude skill. 14 modules: audits scored 0-100, an 18-tactic hook engine, copy graded before you see it, ad diagnosis, GEO, email, launches, pricing. Works in Claude, Codex and Cursor.
genfeed
Plan, write, generate and schedule social content from your Genfeed brand. Bundles the Genfeed MCP server with content skills for X, LinkedIn, Instagram, YouTube and newsletters, and asks for confirmation before anything is scheduled or published.