Maintaining README entries, checking links, reviewing contributions, and making focused Markdown changes in the Awesome-Prompt-Engineering repository.

It keeps repeated editing and review work consistent with the repository’s scope and editorial standards. It also clarifies that the project is a GitHub Pages content repository, not an application.

How natnew/Awesome-Prompt-Engineering configures Claude Code

Q: What is Awesome-Prompt-Engineering CLAUDE.md?

Repository guidance for Claude Code when working on a curated Markdown list about prompt engineering and context engineering for AI agents. It explains the project’s purpose, Claude’s role, and the context that should always be loaded.

Reuse

Borrowing it

Nothing to install: this file belongs to natnew/Awesome-Prompt-Engineering. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/natnew/Awesome-Prompt-Engineering/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/natnew/Awesome-Prompt-Engineering

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/natnew/awesome-prompt-engineering/claude-md/github.svg)](https://agentmods.dev/instructions/natnew/awesome-prompt-engineering/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/natnew/awesome-prompt-engineering/claude-md"><img src="https://agentmods.dev/badge/instructions/natnew/awesome-prompt-engineering/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/natnew/awesome-prompt-engineering/claude-md"><img src="https://agentmods.dev/badge/instructions/natnew/awesome-prompt-engineering/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,295 This file is loaded in full into every session.

When invoked 1,295 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01295	$0.01295
Opus 5.5	$0.00518	$0.00518
Sonnet 5.5	$0.00259	$0.00259
Haiku 4.5	$0.00129	$0.00129

Measured 28d ago against content hash 0297513bc82c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Awesome-Prompt-Engineering 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 28d 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.

CLAUDE.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Awesome-Prompt-Engineering is a curated awesome list for prompt engineering and context engineering for AI agents, published to GitHub Pages with Jekyll (just-the-docs remote theme) at https://natnew.github.io/Awesome-Prompt-Engineering/. README.md is the canonical artefact. Curation beats accumulation.

Authority and routing

AGENTS.md is the canonical operating protocol: scope, trust boundary, quality bar, link rules, decision matrix, review workflows, protected areas. Do not restate it here; read it before any review or README edit. Then load only what the task needs:

Task	Read
README entry add/edit/remove	`.github/instructions/readme-curation.instructions.md`, `link-and-source-quality.instructions.md`
PR / issue review, contributor replies	`.github/instructions/contribution-review.instructions.md`
Typos, wording, small Markdown fixes	`.github/instructions/repository-maintenance.instructions.md`
Contributor requirements (≥60 stars, >30 days old)	`Contributing.md`, `Workflow.md`, `.github/pull_request_template.md`

.github/copilot-instructions.md mirrors these rules for Copilot. If you change a rule, change it in AGENTS.md or the relevant .instructions.md file, not here.

Repository layout

Root *.md topic pages (Basic_Prompting.md, AI_Tools.md, Articles.md, Resources.md, …) are linked from the README Contents table. Each Foo.md renders to Foo.html, so internal links point to .html; do not change them to .md.
foundations/, patterns/, templates/, resources/: long-form learning material.
projects/: worked case studies. Some include Python reference code and pytest suites (projects/core/01_rag_evaluation_pipeline/tests/). This is the only executable code in the repository.
Site machinery: _config.yaml, _layouts/default.html, assets/css/. Protected.
AI Glossary.csv is linked from AI_Glossary.md as a download; keep terms in step when editing either.

Read the full file on GitHub · 106 lines

Changes

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.

28d ago Changed · -3 lines · -62 tokens per session 0297513bc82c
1mo ago Changed · -52 lines · -443 tokens per session 965b6eee820f
1mo ago First seen · 161 lines · 1,800 tokens per session scan A be8457bddde8

Subscribe to this mod's changes

Awesome-Prompt-Engineering CLAUDE.md is an instructions file published in the GitHub repository natnew/Awesome-Prompt-Engineering (114 stars, last pushed 5d ago), licensed MIT. It adds 1,295 tokens to every session, about $0.0052 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 2026-08-30.

Data and AI Prompting Writing and docs ai ai-agents awesome-list first-time-contributors prompt-engineering

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

Awesome-Prompt-Engineering: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Authority and routing

Repository layout

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

vscode model-prompts.instructions.md