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.
/plugin marketplace add bjorn-ingmanson/thefroject-pluginsnpx agentmods add plugins/bjorn-ingmanson/thefroject-plugins/customer-successgit clone --depth 1 https://github.com/bjorn-ingmanson/thefroject-pluginsWrote 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/bjorn-ingmanson/thefroject-plugins/customer-success)<a href="https://agentmods.dev/plugins/bjorn-ingmanson/thefroject-plugins/customer-success"><img src="https://agentmods.dev/badge/plugins/bjorn-ingmanson/thefroject-plugins/customer-success.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
thefroject-customer-success 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 5d 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": "thefroject-customer-success",
"version": "1.0.0",
"description": "Customer success toolkit: churn prevention, health scoring, QBRs, renewal strategy, and escalation frameworks.",
"author": {
"name": "The Froject"
},
"homepage": "https://thefroject.com",
"repository": "https://github.com/bjorn-ingmanson/thefroject-plugins",
"license": "MIT"
}
What it installs
The manifest is a name and a version. 47 skills, 11 commands travel with it, and installing the plugin installs all of them — 2,037 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill customer-success-guide A 35 tokens
- Skill enrich-workspace A 71 tokens
- Skill expansion-opportunity-analyzer A 47 tokens
- Skill health-score-builder A 50 tokens
- Skill idea-to-prd A 86 tokens
- Skill renewal-strategist A 40 tokens
- Skill agent-creator A 76 tokens
- Skill business-case-builder A 15 tokens
- Skill case-study-writer A 16 tokens
- Skill docs-freshness-auditor A 48 tokens
- Skill email-writer A 14 tokens
- Skill escalation-framework A 37 tokens
- Skill feature-adoption-coach A 69 tokens
- Skill meeting-summarizer A 36 tokens
- Skill model-strategy A 49 tokens
- Skill morning-briefing A 17 tokens
- Skill onboarding-guide A 15 tokens
- Skill outputs-triage A 50 tokens
- Skill presentation-builder A 12 tokens
- Skill project-manager A 37 tokens
- Skill qbr-builder A 35 tokens
- Skill quarterly-plan A 54 tokens
- Skill docx-handler A 52 tokens
- Skill pdf-handler A 47 tokens
- Skill plan-tracker A 29 tokens
- Skill customer-billing-ops A 42 tokens
- Skill customer-journey-mapping A 68 tokens
- Skill email-response-simulator A 28 tokens
- Skill renewal-orchestration A 80 tokens
- Skill build-my-profile A 46 tokens
- Skill community-marketing A 63 tokens
- Skill customer-feedback-orchestration A 75 tokens
- Skill diagnose-retention A 43 tokens
- Skill google-workspace-ops A 41 tokens
- Skill churn-prevention A 41 tokens
- Skill context-budget-analyzer A 35 tokens
- Skill debate A 44 tokens
- Skill decision-tracker A 27 tokens
- Skill idea-validator A 46 tokens
- Skill maker-checker A 46 tokens
- Skill meeting-prep-brief A 40 tokens
- Skill pptx-handler A 56 tokens
- Skill quality-gate A 40 tokens
- Skill referral-program-designer A 33 tokens
- Skill extract-my-voice A 37 tokens
- Skill parallel-analyze A 45 tokens
- Skill file-format-converter A 24 tokens
- Command intelligence A 0 tokens
- Command demo-deck A 0 tokens
- Command deal-update A 0 tokens
- Command sow A 0 tokens
- Command stakeholder-update A 0 tokens
- Command outreach A 0 tokens
- Command pipeline-qbr A 0 tokens
- Command brief A 0 tokens
- Command draft A 0 tokens
- Command context-save A 0 tokens
- Command morning-brief A 0 tokens
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.
- 5d ago First seen · 12 lines scan A fc24d63ba295
thefroject-customer-success is a plugin published in the GitHub repository bjorn-ingmanson/thefroject-plugins (1 stars, last pushed 1mo 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
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
knowledge-work-plugins marketplace
Plugin marketplace listing 98 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
container
Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS.
mattpocock-skills
Matt Pocock's agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.