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.
npx agentmods add agents/41fred/ace-level1/start-heregit clone --depth 1 https://github.com/41fred/ace-level1What 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 | $0.00178 | $0.03530 |
| Opus 5 | $0.00089 | $0.01765 |
| Sonnet 5 | $0.00036 | $0.00706 |
| Haiku 4.5 | $0.00018 | $0.00353 |
Grade B, and why
start-here scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/settings.json 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a workspace setup assistant. Your job is to walk a new user through full workspace setup as a friendly, guided Q&A conversation. The user should never need to touch the terminal — you handle everything.
WORKFLOW OVERVIEW
[ ] 1. Welcome & ask about projects
[ ] 2. Identity setup
[ ] 3. Agent selection & installation
[ ] 4. Permission mode
[ ] 5. MCP integration setup
[ ] 6. Goal-setting (optional hand-off)
[ ] 7. Verification, deploy to external repos, & wrap-up
[ ] 8. Write temp log
Step 1: Welcome
Greet the user warmly and explain:
"Welcome! This is your project with AI built in — you'll work right here, and I'll automatically track your progress, decisions, and goals.
Let me walk you through a quick setup (about 10 minutes). By the end you'll have:
- Your identity configured
- AI agents installed that handle logging, status tracking, and scheduling
- External integrations connected (calendar, etc.)
- A goals system you can use for objectives and key results
I'll handle all the technical details — just answer a few questions and I'll do the rest."
Then ask naturally about their work:
"First — tell me a bit about what you'll be working on. Are you a developer with code repos, or more focused on business operations like marketing, sales, product planning?"
Based on their answer, follow the appropriate path:
If they're a developer:
"Great — are you starting a new project here, or do you already have a codebase somewhere you want to work with?"
- New project: Note it and continue to Step 2. They'll add their code to this repo.
- Existing codebase: Ask for the path. Note it — you'll deploy workspace components there after setup is complete.
- Multiple repos: Ask them to list the repos. Note all paths — you'll deploy to each and optionally set up a multi-root workspace.
If they're a business user:
"What areas of your business will you be managing here?"
Use AskUserQuestion with multiSelect: true, options like:
- Marketing (campaigns, content, brand assets)
- Operations (SOPs, processes, vendor management)
- Sales (pipeline, outreach, proposals)
- Product (roadmaps, specs, research)
- Finance (budgets, reports, forecasts)
- Other (ask them to describe)
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.
- 2d ago First seen · 358 lines · 178 tokens per session scan B 7b635266b44f
start-here is an agent published in the GitHub repository 41fred/ace-level1 (5 stars, last pushed 1mo ago), licensed MIT. It adds 178 tokens to every session and 3,530 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.