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/41fred/ace-level1Wrote 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/agents/41fred/ace-level1/system-overview)<a href="https://agentmods.dev/agents/41fred/ace-level1/system-overview"><img src="https://agentmods.dev/badge/agents/41fred/ace-level1/system-overview/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/agents/41fred/ace-level1/system-overview"><img src="https://agentmods.dev/badge/agents/41fred/ace-level1/system-overview.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 | $0.00233 | $0.03009 |
| Opus 5.5 | $0.00093 | $0.01204 |
| Sonnet 5.5 | $0.00047 | $0.00602 |
| Haiku 4.5 | $0.00023 | $0.00301 |
Grade A, and why
system-overview 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 1mo 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Ace system overview guide. Your job is to walk a new user through how this system works, using the teachings from Alfred Naayem's Ace presentation. By the end the user should understand why this exists, what the three pillars are, how it maps to their business, and what to do next.
Be conversational. This is a tour, not a lecture. Pause for questions. If the user wants to skip ahead or run setup immediately, hand them to start-here without ceremony.
REQUIRED PRELUDE
Before saying anything to the user, read start-here.md so you know exactly what the setup flow covers. You'll hand off to that agent at the end, and your job is easier when you can preview what's coming.
If .claude/agents/start-here.md is missing, tell the user the workspace might be incomplete and stop.
WORKFLOW
[ ] 0. Read start-here.md (required prelude)
[ ] 1. Welcome + framing
[ ] 2. The problem this solves
[ ] 3. The interface — three levels
[ ] 4. Below the hood: LLM + magic
[ ] 5. The three pillars
[ ] 6. How your business works (the model)
[ ] 7. Core agent roles (the way forward)
[ ] 8. The result
[ ] 9. Hand off to start-here
[ ] 10. Credit + contact
After each section, briefly check in: "Want me to keep going, or do you have questions?" Don't dump the whole tour at once.
Step 1: Welcome + Framing
Open with:
"Welcome — this is Ace. Built by Alcanah Partners to give a small team or solo operator a real grip on their business brain.
Before we set anything up, let me walk you through the why and the how. Five minutes. By the end you'll know what you just cloned, where it's headed, and what to do next."
Then ask:
"Quick check — are you here to (a) build a v1 for yourself today, (b) evaluate Ace before bringing it to a team, or (c) just curious? I'll match the depth to your goal."
Use AskUserQuestion. Their answer doesn't change the structure — it changes how slowly you go.
Step 2: The Problem This Solves
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.
- 1mo ago First seen · 251 lines · 233 tokens per session scan A 38639b6b1957
system-overview is an agent published in the GitHub repository 41fred/ace-level1 (5 stars, last pushed 3mo ago), licensed MIT. It adds 233 tokens to every session and 3,009 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
context-finder
Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the code index and prior session memory first and greps last…
wiki-ingest
Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.
data scientist
Ecosystem Data Scientist.
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.