Borrowing it
Nothing to install: this file belongs to chenghit/aws-waf-rules-reviewer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chenghit/aws-waf-rules-reviewer/main/AGENTS.mdgit clone --depth 1 https://github.com/chenghit/aws-waf-rules-reviewerWrote 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/chenghit/aws-waf-rules-reviewer/agents-md)<a href="https://agentmods.dev/instructions/chenghit/aws-waf-rules-reviewer/agents-md"><img src="https://agentmods.dev/badge/instructions/chenghit/aws-waf-rules-reviewer/agents-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.
<a href="https://agentmods.dev/instructions/chenghit/aws-waf-rules-reviewer/agents-md"><img src="https://agentmods.dev/badge/instructions/chenghit/aws-waf-rules-reviewer/agents-md.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 | $0.07119 | $0.07119 |
| Opus 5.5 | $0.02848 | $0.02848 |
| Sonnet 5.5 | $0.01424 | $0.01424 |
| Haiku 4.5 | $0.00712 | $0.00712 |
Grade A, and why
aws-waf-rules-reviewer 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 11d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AWS WAF Rules Reviewer
This repository is a tool for AI agents. After reading this file you can review an AWS WAF Web ACL for security issues, misconfigurations, and optimization opportunities, and write a review report. Nothing needs to be installed.
When to use it: the user asks to review, audit, evaluate, or analyze AWS WAF rules or a Web ACL (Chinese: WAF 规则评审、WAF 规则审查、WAF 配置评估、WAF 规则分析). It only covers existing AWS WAF configurations. Don't use it for Cloudflare, other WAF vendors, or migration and conversion work.
When not to use it: if the user is changing this repository's own code or docs, treat it as a normal code repo and skip the workflow. See "Maintaining this repository" at the end.
Language
Reply in the language of the user's message, unless they ask for a specific language. Write the report content in that language too, with one exception: keep the ## Issue N (Severity): heading prefix, the severity words (Critical, Medium, Low, Awareness), and the **Rule**:, **Rules**:, **Current state**:, **Problem**:, and **Recommendation**: labels in English. The scripts parse them. The scripted Chinese findings follow the same convention.
Tools you need
You need to read files, write and append to files, and run shell commands. Use whatever your agent provides for each of these. The steps below say "read", "write", "append", and "run" without naming a specific tool.
Requirements: python3 3.10+ (standard library only). On Windows, use python or py -3 if python3 isn't found. Fetching a Web ACL also needs the AWS CLI with credentials (see Step 0).
Setup: find tool_dir
tool_dir is the directory that contains this AGENTS.md. It's the correct one if {tool_dir}/scripts/waf-preprocess.py exists.
- You loaded this file from disk, for example because the session runs inside this repo or the user gave you a path.
tool_diris that file's directory. - You read this file from a URL and have no local copy. Clone the repo to a temporary directory and use that:
If that directory already exists, rungit clone --depth 1 https://github.com/chenghit/aws-waf-rules-reviewer.git "${TMPDIR:-/tmp}/aws-waf-rules-reviewer"git -C "<dir>" pull --ff-onlyinstead. On Windows, use%TEMP%.
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.
- 11d ago Changed · +1 lines · +181 tokens per session 3878c15662df
- 12d ago Changed · +21 lines · +1,215 tokens per session 908d2b6eca7f
- 26d ago Changed · +4 lines · +297 tokens per session 1a3a36ab3299
- 27d ago Changed · +9 lines · +747 tokens per session 6691e07d9499
- 28d ago First seen · 257 lines · 4,679 tokens per session scan A 1f62bef8afaf
aws-waf-rules-reviewer AGENTS.md is an instructions file published in the GitHub repository chenghit/aws-waf-rules-reviewer (9 stars, last pushed 11d ago), licensed MIT. It adds 7,119 tokens to every session, about $0.0285 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 2026-09-30.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.