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/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/compounding-marketing)<a href="https://agentmods.dev/plugins/classicchins/compounding-marketing/compounding-marketing"><img src="https://agentmods.dev/badge/plugins/classicchins/compounding-marketing/compounding-marketing/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/classicchins/compounding-marketing/compounding-marketing"><img src="https://agentmods.dev/badge/plugins/classicchins/compounding-marketing/compounding-marketing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
compounding-marketing 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 2mo 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": "compounding-marketing",
"version": "1.6.0",
"description": "61 marketing skills + 16 workflow commands for B2B SaaS: positioning, messaging, copywriting, CRO, SEO, GTM, lifecycle. Opt-in install with /cm-setup and full /cm-uninstall rollback.",
"author": {
"name": "Chinmaya Shankar",
"email": "[email protected]",
"url": "https://github.com/classicchins/compounding-marketing"
},
"homepage": "https://github.com/classicchins/compounding-marketing",
"repository": "https://github.com/classicchins/compounding-marketing",
"license": "MIT",
"keywords": [
"marketing",
"saas-marketing",
"positioning",
"messaging",
"copywriting",
"cro",
"conversion-rate-optimization",
"seo",
"gtm",
"go-to-market",
"compound-marketing",
"mcp"
],
"components": {
"skills": 61,
"commands": 16
},
"commands": "./commands/",
"skills": "./skills/"
}
What it installs
The manifest is a name and a version. 39 skills, 16 commands travel with it, and installing the plugin installs all of them — 1,988 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill abm-strategy A 66 tokens
- Skill email-deliverability A 75 tokens
- Skill marketing-psychology A 44 tokens
- Skill ad-creative A 42 tokens
- Skill analytics-tracking A 48 tokens
- Skill attribution-modeling A 45 tokens
- Skill brand-voice A 52 tokens
- Skill case-study A 45 tokens
- Skill churn-prevention A 41 tokens
- Skill cm-context A 60 tokens
- Skill competitive-analysis A 44 tokens
- Skill competitor-alternatives A 57 tokens
- Skill competitor-content-monitoring A 54 tokens
- Skill copy-editing A 60 tokens
- Skill copywriting A 55 tokens
- Skill customer-interview A 49 tokens
- Skill email-sequence A 42 tokens
- Skill form-cro A 55 tokens
- Skill free-tool-strategy A 45 tokens
- Skill gtm-strategy A 58 tokens
- Skill icp-research A 52 tokens
- Skill launch-strategy A 48 tokens
- Skill linkedin-ads A 52 tokens
- Skill market-sizing A 57 tokens
- Skill marketing-automation A 66 tokens
- Skill marketing-ideas A 46 tokens
- Skill onboarding-cro A 48 tokens
- Skill page-cro A 45 tokens
- Skill ab-test-setup A 40 tokens
- Skill ai-seo A 58 tokens
- Skill channel-strategy A 46 tokens
- Skill community-strategy A 43 tokens
- Skill content-performance-scoring A 53 tokens
- Skill content-strategy A 45 tokens
- Skill customer-research A 58 tokens
- Skill lead-magnets A 48 tokens
- Skill messaging-framework A 53 tokens
- Skill newsletter-growth A 47 tokens
- Skill cold-email A 46 tokens
- Command cm-compound A 0 tokens
- Command cm-setup A 0 tokens
- Command cm-weekly A 0 tokens
- Command cm-audit A 0 tokens
- Command cm-retro A 0 tokens
- Command cm-sprint A 0 tokens
- Command cm-eod A 0 tokens
- Command cm-standup A 0 tokens
- Command cm-daily A 0 tokens
- Command cm-email A 0 tokens
- Command cm-social A 0 tokens
- Command cm-copy A 0 tokens
- Command cm-launch A 0 tokens
- Command cm-position A 0 tokens
- Command cm-research A 0 tokens
- Command cm-uninstall C 0 tokens
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.
- 2mo ago First seen · 34 lines scan A 8249740cd41d
compounding-marketing is a plugin published in the GitHub repository classicchins/compounding-marketing (8 stars, last pushed 5mo 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.
compounding-marketing compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| compounding-marketingclassicchins/compounding-marketing | Plugin | 8 | 5mo ago | MIT | A | — | Claude Code |
| humanizerblader/humanizer | Plugin | 65k | 10d ago | MIT | A | — | Claude Code |
| claude-plugins-official marketplaceanthropics/claude-plugins-official | Plugin | 46k | yesterday | Apache-2.0 | A | — | Claude Code |
| nextjsvercel/next.js | Plugin | 143k | yesterday | MIT | A | — | Claude Code |
| themes-examplegoogle-gemini/gemini-cli | Plugin | 109k | yesterday | Apache-2.0 | A | — | Gemini CLI |
| knowledge-work-plugins marketplaceanthropics/knowledge-work-plugins | Plugin | 35k | 3d ago | Apache-2.0 | A | — | Claude Code |
| code-modernizationanthropics/claude-plugins-official | Plugin | 46k | yesterday | Apache-2.0 | A | — | Claude Code |