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/timothywarner-org/prompt-pro/copilot-instructionsgit clone --depth 1 https://github.com/timothywarner-org/prompt-proWrote 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/timothywarner-org/prompt-pro/copilot-instructions)<a href="https://agentmods.dev/instructions/timothywarner-org/prompt-pro/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/timothywarner-org/prompt-pro/copilot-instructions.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 | $0.00731 | $0.00731 |
| Opus 5 | $0.00365 | $0.00365 |
| Sonnet 5 | $0.00146 | $0.00146 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
prompt-pro copilot-instructions.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 5d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prompt-pro AI guidance
Purpose and scope
- This is a content-first repository. It backs Tim Warner's O'Reilly Live Learning course How to Prompt Like a Pro (4 x 50-minute segments).
- The course teaches Warner's 26 Laws of Generative AI, split 7-7-8-4 across the four segments (see ../WARNERS-LAWS.md).
- All demo content uses the fictional Contoso Robotics scenario (mid-size robotics manufacturer, 500 employees, $120M revenue, Austin TX, CEO Maria Chen). Keep new demo material consistent with this fiction.
- There is no top-level application. The root
package.jsonis a legacy stub - do not run itsstart/dev/testscripts.
Repository layout
segments/segment-1-identity-mindset-context/- Laws 1-7, Contoso scenario data and demos.segments/segment-2-context-sculpting-technique/- Laws 8-14, few-shot, chain-of-thought, role-play.segments/segment-3-workflow-multimodal-security/- Laws 15-22, custom instructions, prompt versioning, privacy audits (includes a vendoredknowledge/subfolder of Microsoft Learn content - do not edit it).segments/segment-4-agentic-orchestration/- Laws 23-26, LLM matching, subagents, checkpoints.docs/- Long-form reference guides and the master slide deck.images/- Cover art and social preview (optimized PNG/JPG).
Drop new material into the matching segment folder rather than introducing parallel directories.
The only runnable code
The single piece of executable code is the MCP server under segments/segment-4-agentic-orchestration/mcp-demos/weather-server/:
npm install- install@modelcontextprotocol/sdkandzod.npm start- run the MCP server (node server.js).npm run inspect- launch MCP Inspector against the local server.
Everything else in the repo is Markdown lesson content, reference docs, or assets.
Authoring rules
- Two-space list indentation; keep a blank line before and after headings, lists, and fenced code blocks (enforced by ../markdownlint.json).
- Sentence-case headings; kebab-case directories and filenames.
- Prefer short sections with tables or callouts so lessons stay scannable on screen shares.
- Use relative links for assets and cross-references.
- Never embed real API keys in lesson text. Reference
env.exampleand remind learners to set their own environment variables.
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.
- 5d ago First seen · 51 lines · 731 tokens per session scan A 64f5828d74dd
prompt-pro copilot-instructions.md is an instructions file published in the GitHub repository timothywarner-org/prompt-pro (47 stars, last pushed 2mo ago), licensed MIT. It adds 731 tokens to every session, about $0.0037 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 instructions, from other repositories
prompts.chat AGENTS.md
AGENTS.md instructions for f/prompts.chat, covering agents.md, project overview, tech stack, project structure and commands.
wanaku CLAUDE.md
Claude Code instructions for wanaku-ai/wanaku, covering wanaku, core guidelines, quick start, build info and architecture.
ase AGENTS.md
AGENTS.md instructions for rse/ase, covering about, repository layout, build system, setup and cli commands.
OpenHands AGENTS.md
AGENTS.md instructions for OpenHands/OpenHands, covering repository notes, general, repository map — what belongs where, cross-repository boundaries and pr description human check.
ai-native-sdlc AGENTS.md
Instructions for bashebr/ai-native-sdlc, covering agents.md, source of truth, validation and conventions.
repo2skill AGENTS.md
Instructions for Hhhkarimi/repo2skill, a project described as: Turn any public GitHub repository into professional, repository-native Agent Skills for ChatGPT and Claude - free, browser-first, no AI API required.