Borrowing it
Nothing to install: this file belongs to nolindnaidoo/regex-le. 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/nolindnaidoo/regex-le/main/AGENTS.mdgit clone --depth 1 https://github.com/nolindnaidoo/regex-leWrote 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/nolindnaidoo/regex-le/agents-md)<a href="https://agentmods.dev/instructions/nolindnaidoo/regex-le/agents-md"><img src="https://agentmods.dev/badge/instructions/nolindnaidoo/regex-le/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/nolindnaidoo/regex-le/agents-md"><img src="https://agentmods.dev/badge/instructions/nolindnaidoo/regex-le/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 | $0.06874 | $0.06874 |
| Opus 5.5 | $0.02750 | $0.02750 |
| Sonnet 5.5 | $0.01375 | $0.01375 |
| Haiku 4.5 | $0.00687 | $0.00687 |
Grade A, and why
regex-le 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 3d 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- dates-le AGENTS.md — 91% identical, 109 lines differ
- secrets-le AGENTS.md — 89% identical, 98 lines differ
- string-le AGENTS.md — 88% identical, 110 lines differ
- urls-le AGENTS.md — 86% identical, 119 lines differ
- scrape-le AGENTS.md — 83% identical, 127 lines differ
- paths-le AGENTS.md — 81% identical, 101 lines differ
- colors-le AGENTS.md — 80% identical, 114 lines differ
- numbers-le AGENTS.md — 78% identical, 107 lines differ
How it starts
The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Regex-LE
Technical source of truth for this repo. README.md is the user-facing doc; this file is for anyone (human or agent) changing the code.
This repo hosts two products: the extension at the root (this document's scope) and the Rust CLI in crate/ (its own AGENTS.md + SPEC.md). The crate ports the lint half only — pattern detection and the ReDoS screen, never the tester. The shared corpus lives at crate/fixtures/; scripts/check-extraction-parity.ts fails CI when this extension drifts from it.
The Rust CLI also ships a second way, through npm: src/cli/ is its terminal surface rebuilt over this extension's extraction and ReDoS engine, bundled to cli/cli.js as the npm package regex-le. Both install a command named regex-le, so the npm one is held to the crate's surface byte for byte, which is a different contract from the extraction parity above. src/cli/ follows crate/src/cli.rs, scan.rs, walk.rs and mcp/, not the extension's commands: it ends the run on a directory it cannot enter, and asks extractRegexPatternsOrRefuse, which refuses a constructor or call argument past the crate's parser bounds (255 nested groups, 5,000 alternation branches) by name, as the shared extract_patterns tool now does too. The editor commands keep extractRegexPatterns, which drops such a pattern. scripts/check-cli-parity.ts runs both binaries over one generated tree and fails on any difference in stdout, stderr or exit code, and on any byte of difference in what regex-le mcp writes. One gap is known and left out of it: the crate's extraction regexes run under a backtracking budget and can give up on a file, and JavaScript's have none. scripts/check-cli-pipes.ts, shared with every port, closes stdout or stderr before either binary writes and fails on any difference in what follows, on all three operating systems. A change to the crate's surface changes src/cli/ in the same commit.
What this is
A VS Code extension that finds regex patterns in the active document (literals, new RegExp(...), RegExp(...)), tests them against the file content, and screens them for catastrophic backtracking by demonstration. No network access, no filesystem writes.
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.
- 3d ago Changed · +12 lines · +813 tokens per session 1cdc183ac2e7
- 7d ago Changed · +54 tokens per session ddff551959e9
- 13d ago Changed · +1 lines · +354 tokens per session cc12438635c7
- 16d ago Changed · -6 lines · -182 tokens per session fc87e0fcd6ce
- 19d ago Changed · +21 tokens per session 4fc16667df21
- 21d ago Changed · +74 tokens per session 68116824b920
- 22d ago Changed · +19 lines · +303 tokens per session bf074fa1e837
- 1mo ago First seen · 323 lines · 5,437 tokens per session scan A dc1f9b2b7d79
regex-le AGENTS.md is an instructions file published in the GitHub repository nolindnaidoo/regex-le (2 stars, last pushed 4d ago), licensed MIT. It adds 6,874 tokens to every session, about $0.0275 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 2026-08-31.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.