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/ammonhaggerty/ai-coding-primer/claude-mdgit clone --depth 1 https://github.com/ammonhaggerty/ai-coding-primerWrote 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/ammonhaggerty/ai-coding-primer/claude-md)<a href="https://agentmods.dev/instructions/ammonhaggerty/ai-coding-primer/claude-md"><img src="https://agentmods.dev/badge/instructions/ammonhaggerty/ai-coding-primer/claude-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 | $0.00545 | $0.00545 |
| Opus 5 | $0.00272 | $0.00272 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
ai-coding-primer CLAUDE.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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repository.
Repository Structure
ai-coding-primer/
├── guidebook/ # The guidebook — one markdown file per chapter (00-08)
├── starter/ # Starter project template
├── assets/ # Images and diagrams
├── docs/ # Working notes, plans, progress (project memory)
├── _authoring/ # Editorial materials (outlines, research, notes — not reader-facing)
├── CLAUDE.md # This file
├── CONTRIBUTING.md # Contributor guide
└── README.md # Project overview
Guidebook Chapters
Flat files in guidebook/, numbered for reading order:
00-tldr.md— TL;DR Fast Track01-about-the-author.md— About the Author02-the-landscape.md— The Landscape03-setting-up.md— Setting Up Your Workshop04-the-cloud.md— The Cloud05-building.md— Building06-daily-practice.md— The Daily Practice07-where-this-is-going.md— Where This Is Going08-appendices.md— Appendices
Constraints
- Companion plugin:
a-primer-skills(separate repo: github.com/ammonhaggerty/a-primer-skills) - Always use D1, never Turso
- DaisyUI 5 via CDN —
card-borderdoesn't work, useborder border-base-300 - Theme:
emerald - Cookies:
secure: falsein local dev,secure: truein production - Opus 4.8 recommended for all coding (available on Pro and Max; Pro defaults to Sonnet — switch via /model)
- Recommend
mediumeffort for most coding tasks (faster, fewer tokens; step up for hard problems) - Do not recommend OpenAI for anything
- Image generation: Google Gemini / Imagen
- Voice: ElevenLabs, Deepgram, Cartesia
Writing Tone
- Practical, grounded, zero hype
- Audience is non-technical — explain everything
- Prescriptive and opinionated — specific recommendations with reasoning
- Honest about costs, limits, and breakage
- Minimal formatting — prose over bullet points
Working Memory
Save progress notes, plans, and brainstorming to docs/. Read docs/ at the start of sessions to recover context. Keep this CLAUDE.md lean — rules and constraints only.
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 · 57 lines · 545 tokens per session scan A d1ba873b5506
ai-coding-primer CLAUDE.md is an instructions file published in the GitHub repository ammonhaggerty/ai-coding-primer (79 stars, last pushed 1mo ago), licensed MIT. It adds 545 tokens to every session, about $0.0027 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
claude-code-templates CLAUDE.md
Claude Code instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.
codexspec CLAUDE.md
Claude Code instructions for Zts0hg/codexspec, covering claude.md - codexspec development guide, project overview, purpose, technology stack and architecture.
hqbase AGENTS.md
AGENTS.md instructions for HQBase/hqbase, covering hqbase workspace guide, boundaries and quality gate.
ctxlayer CLAUDE.md
Claude Code instructions for stevenn/ctxlayer, covering ctxlayer — claude code briefing, what runs where, architecture pointers, how a claude session should work in this repo and conventions.
titen CLAUDE.md
Instructions for RamaAditya49/titen, covering claude.md, read agents.md first, commands, two runtimes, one core and publishing to npm.
trellis AGENTS.md
Instructions for craigcossairt/trellis, covering agents.md , project, what i need from agents, current state - source of truth pointers and tech stack.