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/commands/jeremylongshore/tons-of-skills-marketplace/discovery)<a href="https://agentmods.dev/commands/jeremylongshore/tons-of-skills-marketplace/discovery"><img src="https://agentmods.dev/badge/commands/jeremylongshore/tons-of-skills-marketplace/discovery/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/commands/jeremylongshore/tons-of-skills-marketplace/discovery"><img src="https://agentmods.dev/badge/commands/jeremylongshore/tons-of-skills-marketplace/discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00007 | $0.02040 |
| Opus 5 | $0.00003 | $0.01020 |
| Sonnet 5 | $0.00001 | $0.00408 |
| Haiku 4.5 | $0.00001 | $0.00204 |
Grade A, and why
discovery 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery Questionnaire Generator
Generate comprehensive discovery questionnaires tailored to AI agency prospects.
Usage
When a user requests a discovery questionnaire, create a customized set of questions based on the project type, client industry, and engagement scope.
Questionnaire Structure
1. Business Context (Understanding the Client)
- Company overview and history
- Current business model
- Market position and competitors
- Growth goals and challenges
- Decision-making process
2. Current State Assessment
- Existing tools and systems
- Current workflows and processes
- Pain points and bottlenecks
- Manual processes ripe for automation
- Data sources and integrations
3. Project Goals & Objectives
- Primary objectives
- Success metrics (KPIs)
- Timeline and urgency
- Budget range
- Expected ROI
4. Technical Environment
- Existing tech stack
- API access and documentation
- Data security requirements
- Compliance needs (GDPR, HIPAA, etc.)
- IT/development team involvement
5. Team & Stakeholders
- Key stakeholders and roles
- End users of the solution
- Decision makers
- Implementation team
- Training requirements
6. Scope & Deliverables
- Must-have features
- Nice-to-have features
- Out of scope
- Integration requirements
- Ongoing support needs
Questionnaire Templates
AI Automation Project
# Discovery Questionnaire: AI Automation Project
## Client Information
- Company Name:
- Industry:
- Company Size:
- Contact Name & Role:
- Project Sponsor:
## Business Context
1. What is your company's primary business model?
2. What are your top 3 business goals for the next 12 months?
3. What challenges are preventing you from achieving these goals?
4. How do you currently measure success in your operations?
## Current State
5. What processes consume the most time in your organization?
6. Which of these processes are currently manual?
7. What tools/software do you currently use for these processes?
8. What pain points do you experience with current solutions?
9. Have you attempted automation before? What were the results?
## Project Vision
10. What specific process do you want to automate?
11. What would success look like for this project?
12. How many people are involved in this process currently?
13. How much time per week is spent on this process?
14. What is the estimated time/cost savings you expect?
## Technical Requirements
15. What systems need to be integrated? (List all)
16. Do you have API access to these systems?
17. What is your current data infrastructure? (Cloud, on-premise, hybrid)
18. Are there any security or compliance requirements we should know about?
19. Who will manage the solution after implementation?
## Stakeholders & Users
20. Who are the end users of this automation?
21. What is their technical skill level?
22. Who needs to approve this project?
23. What is the typical decision-making timeline?
24. Will we have direct access to end users for feedback?
## Scope & Timeline
25. What is your ideal launch date?
26. Are there any hard deadlines we should be aware of?
27. What features are absolutely required for v1.0?
28. What features can wait for future phases?
29. What is your budget range for this project?
## Post-Launch
30. What level of ongoing support do you expect?
31. Who will handle day-to-day maintenance?
32. How do you envision scaling this solution?
33. What metrics will you use to measure ROI?
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.
- 12d ago First seen · 323 lines · 7 tokens per session scan A 9780ad0a712d
discovery is a command published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 2,040 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
init
Initialize project documentation, preferences, or design tokens.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
test-coverage
Analyze test coverage and identify the highest-value gaps to fill.
setup
Diagnose-first project setup with state machine — scans, confirms, interviews, writes.
start-10-1
A guided lesson on setting up clasp, a command-line tool for managing Google Apps Script projects, and connecting it to Google’s Apps Script API.
flow-diff
Detail differences in nodes, connections, and parameter keys between two workflow JSON files.