Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.
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/jeremylongshore/tons-of-skills-marketplaceWrote 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/jeremylongshore/tons-of-skills-marketplace/tonone)<a href="https://agentmods.dev/plugins/jeremylongshore/tons-of-skills-marketplace/tonone"><img src="https://agentmods.dev/badge/plugins/jeremylongshore/tons-of-skills-marketplace/tonone/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/jeremylongshore/tons-of-skills-marketplace/tonone"><img src="https://agentmods.dev/badge/plugins/jeremylongshore/tons-of-skills-marketplace/tonone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
tonone 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- tonone — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "tonone",
"description": "Engineering + Product + Operations + Legal + Design + Data Science + Security Operations + Developer Experience + Infrastructure Specialist + AI Operations team \u2014 100 agents as Claude Code specialists. Infrastructure, DevOps, backend, security, ML/AI, mobile, UX, analytics, growth, revenue, content, PR, customer success, finance, people, operations, support, contracts, compliance, IP, governance, regulatory, color systems, typography, motion, accessibility, design tokens, forecasting, feature engineering, model training, drift monitoring, vector search, LLM fine-tuning, pen testing, detection engineering, incident response, zero trust, API docs, SDK design, developer onboarding, Kubernetes, Terraform, FinOps, service mesh, edge computing, caching, queuing, multi-cloud, chaos engineering, model deployment, LLM evaluation, AI observability, guardrails, prompt engineering, embeddings, ranking, and more.",
"version": "1.9.1",
"author": {
"name": "tonone-ai",
"url": "https://tonone.ai"
},
"repository": "https://github.com/tonone-ai/tonone",
"license": "MIT",
"keywords": [
"agents",
"engineering-team",
"infrastructure",
"devops",
"backend",
"security",
"observability",
"frontend",
"ml",
"mobile",
"embedded",
"analytics",
"testing",
"platform",
"sales",
"revenue",
"customer-success",
"content-marketing",
"pr",
"community",
"finance",
"people",
"operations",
"support"
],
"hooks": {
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": "bash \"${CLAUDE_PLUGIN_ROOT}/hooks/install-statusline.sh\""
},
{
"type": "command",
"command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/tonone-update-check.js\"",
"timeout": 8
},
{
"type": "command",
"command": "node \"${CLAUDEWhat it installs
The manifest is a name and a version. 100 agents, 9 plugins travel with it, and installing the plugin installs all of them — 6,033 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Agent apex A 48 tokens
- Agent form A 61 tokens
- Agent helm A 61 tokens
- Agent volt A 67 tokens
- Agent atlas A 48 tokens
- Agent buzz A 55 tokens
- Agent deal A 65 tokens
- Agent draft A 64 tokens
- Agent ink A 57 tokens
- Agent keep A 59 tokens
- Agent proof A 84 tokens
- Agent spine A 63 tokens
- Agent brace A 54 tokens
- Agent cortex A 75 tokens
- Agent echo A 61 tokens
- Agent flux A 60 tokens
- Agent folk A 63 tokens
- Agent keel A 57 tokens
- Agent lens A 53 tokens
- Agent lumen A 63 tokens
- Agent mint A 69 tokens
- Agent pave A 72 tokens
- Agent pitch A 67 tokens
- Agent prism A 78 tokens
- Agent touch A 63 tokens
- Agent vigil A 68 tokens
- Agent warden A 58 tokens
- Agent forge A 59 tokens
- Agent relay A 60 tokens
- Agent surge A 62 tokens
- Agent bind A 60 tokens
- Agent brief A 57 tokens
- Agent cache A 56 tokens
- Agent change A 57 tokens
- Agent chaos A 54 tokens
- Agent cite A 61 tokens
- Agent compat A 62 tokens
- Agent frame A 63 tokens
- Agent gate A 71 tokens
- Agent mesh A 68 tokens
- Agent multi A 68 tokens
- Agent onboard A 71 tokens
- Agent phish A 58 tokens
- Agent port A 70 tokens
- Agent scope A 63 tokens
- Agent shield A 61 tokens
- Agent terms A 59 tokens
- Agent zero A 67 tokens
- Agent audit A 55 tokens
- Agent axe A 53 tokens
- Agent bench A 58 tokens
- Agent blue A 59 tokens
- Agent budget A 52 tokens
- Agent cast A 45 tokens
- Agent chain A 56 tokens
- Agent clause A 63 tokens
- Agent clean A 55 tokens
- Agent copy A 60 tokens
- Agent cut A 52 tokens
- Agent deploy A 61 tokens
- Agent drift A 54 tokens
- Agent edge A 56 tokens
- Agent embed A 55 tokens
- Agent eval A 53 tokens
- Agent evals A 59 tokens
- Agent feat A 56 tokens
- Agent finop A 59 tokens
- Agent fit A 57 tokens
- Agent glyph A 48 tokens
- Agent grid A 47 tokens
- Agent guard A 56 tokens
- Agent guide A 51 tokens
- Agent hue A 51 tokens
- Agent hunt A 52 tokens
- Agent kube A 59 tokens
- Agent lodge A 59 tokens
- Agent mark A 54 tokens
- Agent mock A 62 tokens
- Agent move A 67 tokens
- Agent patch A 72 tokens
- Agent plot A 66 tokens
- Agent prompt A 70 tokens
- Agent queue A 58 tokens
- Agent rank A 57 tokens
- Agent red A 58 tokens
- Agent resp A 59 tokens
- Agent sample A 54 tokens
- Agent sast A 70 tokens
- Agent schema A 77 tokens
- Agent score A 51 tokens
- Agent serv A 64 tokens
- Agent siem A 60 tokens
- Agent terra A 52 tokens
- Agent token A 60 tokens
- Agent tone A 63 tokens
- Agent trace A 60 tokens
- Agent tune A 74 tokens
- Agent vect A 59 tokens
- Agent wire A 61 tokens
- Agent crest C 64 tokens
- Plugin devx-team A not measured
- Plugin engineering-team A not measured
- Plugin full-team A not measured
- Plugin infra-specialist-team A not measured
- Plugin legal-team A not measured
- Plugin ai-ops-team A not measured
- Plugin data-science-team A not measured
- Plugin design-team A not measured
- Plugin marketing-team 8 inside A not measured
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.
- 9d ago First seen · 114 lines scan A 95a00ffe48e7
tonone is a plugin published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), 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 2026-09-03.
Other plugins, from other repositories
jk
GitHub CLI-style interface for Jenkins controllers - create multibranch jobs, inspect config.xml, and manage runs, logs, artifacts, credentials, nodes, and queues.
jarvis-deep-interview
Convergent Socratic interview with mathematical ambiguity gating. 8-15 narrowing rounds + Contrarian/Simplifier Challenge Mode + JSONL decision log. Inspired by Sorbh/interview-me.
looptimal
Turns an objective into a delivered, VERIFIED OUTCOME: frames a hash-pinned sealed acceptance suite, designs the right loop (the loop-design wizard, formerly LoopPrint), war-games it forward, executes with dynamic domain-expert sub-agents (maker != checker), and gates completion on a separate verifier re-running the…
claude-superskills marketplace
Plugin marketplace listing 1 plugin: claude-superskills.
lv
Compatibility namespace for the Elixir/Phoenix plugin's /lv: commands.
git-commit
A Git commit process that stages changes, runs three parallel reviews, creates the commit, and pushes it. Git is the system used to track code changes.