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 instructions/haozhang615/ads-copilot/agents-mdgit clone --depth 1 https://github.com/HaoZhang615/ads-copilotWrote 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/instructions/haozhang615/ads-copilot/agents-md)<a href="https://agentmods.dev/instructions/haozhang615/ads-copilot/agents-md"><img src="https://agentmods.dev/badge/instructions/haozhang615/ads-copilot/agents-md.svg" alt="Measured on agentmods" 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 | $0.01615 | $0.01615 |
| Opus 5 | $0.00807 | $0.00807 |
| Sonnet 5 | $0.00323 | $0.00323 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
ads-copilot AGENTS.md 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 4d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidelines for AI agents operating in this repository.
Repository Overview
ADS Copilot — voice-enabled AI copilot for Architecture Design Sessions. FastAPI/WebSocket backend + Next.js 15 frontend. Ships with three domain skills: Azure Databricks, Microsoft Fabric, and Microsoft Foundry.
- Backend:
app/backend/— FastAPI, async/await, Copilot SDK agent, WebSocket endpoint - Frontend:
app/frontend/— Next.js 15 / React 19 / Tailwind CSS 4, App Router - Skills:
skills/databricks-ads-session/,skills/fabric-ads-session/,skills/foundry-ads-session/— domain knowledge + Mermaid generators - Mirror skills:
.github/skills/— duplicates for GitHub Copilot discovery (must stay in sync) - Infra:
infra/— Azure Bicep IaC
Build / Lint / Test Commands
No linter, formatter, or test framework is configured. Validation is manual.
Backend
cd app/backend && pip install -r requirements.txt # Install
python -m uvicorn app.backend.main:app --reload # Dev server (from repo root)
python -c "import py_compile; py_compile.compile('app/backend/main.py', doraise=True)" # Compile check
Frontend
cd app/frontend
npm install
npm run dev # Dev server on :3000
npm run build # Production build (validates TypeScript + Next.js)
Docker / Azure
cp .env.sample .env && cd app && docker compose up --build # Local stack
azd auth login && azd up # Azure deployment
Diagram Generator (Skill Scripts)
python skills/databricks-ads-session/scripts/generate_architecture.py --list # List patterns
python skills/databricks-ads-session/scripts/generate_architecture.py --pattern medallion # Generate one
python skills/fabric-ads-session/scripts/generate_architecture.py --list # Fabric patterns
python skills/foundry-ads-session/scripts/generate_architecture.py --list # Foundry patterns
python skills/foundry-ads-session/scripts/generate_architecture.py --pattern baseline-chat # Generate one
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.
- 4d ago First seen · 131 lines · 1,615 tokens per session scan A 8a35756b8006
ads-copilot AGENTS.md is an instructions file published in the GitHub repository HaoZhang615/ads-copilot (2 stars, last pushed 6mo ago), licensed MIT. It adds 1,615 tokens to every session, about $0.0081 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 2026-08-31.
Other instructions, from other repositories
apex-accelerator agent-skills.instructions.md
Guidelines for creating high-quality Agent Skills for GitHub Copilot.
apex-accelerator context-optimization.instructions.md
Context window optimization rules for agent definitions, skills, and instruction files.
apex-accelerator AGENTS.md
AGENTS.md instructions for jonathan-vella/apex-accelerator, covering apex, setup commands, clone the accelerator template and open in dev container, https://github.com/jonathan-vella/apex-accelerator and build & validation.
apex-accelerator no-interactive-shell.instructions.md
Prevents interactive shell prompts and long-output terminal replays from being injected into chat. Forbids -i flags on mv/rm/cp, read -p, and confirm prompts (incl. inside bash -c '...'). Pipe long output to files. Scoped to chat-context-loaded files; skill references/ and templates/ are exempt because they hold…
apex-accelerator vendor-prompting.instructions.md
Vendor prompting best-practice rules for Anthropic Claude and OpenAI GPT-5.6-Terra agents and prompts. Each rule cites a rule ID in the vendor-prompting skill rules.json registry. Validator: npm run lint:vendor-prompting.
apex-accelerator github-actions.instructions.md
Project-specific standards for GitHub Actions workflows in this repository.