Borrowing it
Nothing to install: this file belongs to nolindnaidoo/numbers-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/numbers-le/main/AGENTS.mdgit clone --depth 1 https://github.com/nolindnaidoo/numbers-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/numbers-le/agents-md)<a href="https://agentmods.dev/instructions/nolindnaidoo/numbers-le/agents-md"><img src="https://agentmods.dev/badge/instructions/nolindnaidoo/numbers-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/numbers-le/agents-md"><img src="https://agentmods.dev/badge/instructions/nolindnaidoo/numbers-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 | $0.06967 | $0.06967 |
| Opus 5.5 | $0.02787 | $0.02787 |
| Sonnet 5.5 | $0.01393 | $0.01393 |
| Haiku 4.5 | $0.00697 | $0.00697 |
Grade A, and why
numbers-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 2d 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.
This is a copy
78% identical to regex-le AGENTS.md — 107 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Numbers-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 shared extraction corpus lives at crate/fixtures/, and it pins how a number is printed as well as which numbers are found; 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 engine, bundled to cli/cli.js as the npm package numbers-le. Both install a command named numbers-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, extract/format.rs, extract/locate.rs and mcp/, not the extension's commands: it resolves formats as the crate does (.env.local is dotenv), reports every JSON number token as the crate's syntax-tree walk does (a repeated key included), and its text scan takes Rust's Unicode \d. 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 numbers-le mcp writes. The one thing it does not compare is the wording after Failed to parse <FORMAT>: when a parser refuses a document, and it leaves out the corpus documents crate/SPEC.md lists as deliberate divergences, which the npm CLI reads as this extension does. 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 extracts numeric values from the active document into a results editor, with dedupe/sort post-processing and per-column CSV fan-out. Six parsed formats (JSON, YAML, CSV, TOML, INI, .env), a numeric-literal reader for twelve source languages, and a grammar-less text scan for everything else. 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.
- 2d ago Changed · +3 lines · +75 tokens per session b0b261087e02
- 4d ago Changed · +13 lines · +763 tokens per session 3259ea51bfce
- 7d ago Changed · +54 tokens per session 47b8327e74dd
- 13d ago Changed · +1 lines · +354 tokens per session ce9b93136d27
- 15d ago Changed · -6 lines · -182 tokens per session 6f227245d573
- 19d ago Changed · +26 tokens per session 83a45c634adc
- 21d ago Changed · +74 tokens per session 0a655ba076d2
- 22d ago Changed · +19 lines · +303 tokens per session 0f16aba819d2
- 1mo ago First seen · 332 lines · 5,500 tokens per session scan A b8e2a7ffe4ff
numbers-le AGENTS.md is an instructions file published in the GitHub repository nolindnaidoo/numbers-le (1 stars, last pushed 3d ago), licensed MIT. It adds 6,967 tokens to every session, about $0.0279 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 78% identical to regex-le AGENTS.md, differing in 107 lines, and is treated as a copy.
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.