Borrowing it
Nothing to install: this file belongs to braswelljr/rmx. 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/braswelljr/rmx/main/AGENTS.mdgit clone --depth 1 https://github.com/braswelljr/rmxWrote 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/braswelljr/rmx/agents-md)<a href="https://agentmods.dev/instructions/braswelljr/rmx/agents-md"><img src="https://agentmods.dev/badge/instructions/braswelljr/rmx/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/braswelljr/rmx/agents-md"><img src="https://agentmods.dev/badge/instructions/braswelljr/rmx/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 | $0.03116 | $0.03116 |
| Opus 5.5 | $0.01246 | $0.01246 |
| Sonnet 5.5 | $0.00623 | $0.00623 |
| Haiku 4.5 | $0.00312 | $0.00312 |
Grade A, and why
rmx 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 1mo 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to agents when working with code in this repository.
Project Overview
rmx (github.com/braswelljr/rmx) is a cross-platform, drop-in replacement for the
GNU/UNIX rm command. It mirrors rm's flag surface and semantics — prompting, recursion,
write-protected handling, --preserve-root, faithful diagnostics — while adding concurrent
removal on the non-interactive path.
It is a single top-level command invoked as rmx [OPTION]... [FILE]..., exactly like rm.
Architecture at a glance
Two layers:
core/— one correct removal engine. Owns the tree walk, prompting, permission checks, diagnostics and concurrency. Everything routes through it.cmd/— one package per flag (cmd/force,cmd/interactive, …). Each package is a thin adapter: it registers its flag(s) and folds the parsed value into a singlecore.Options.cmd/execute.gocomposes them and runs the engine once.
This split keeps flag composition (rmx -rvf, -ri) correct: there is exactly one walk, driven
by one core.Options, rather than each flag re-implementing traversal.
Project Structure
rmx/
main.go # Thin entry point; //go:generate hook for docs
cmd/ # One package per flag (adapters over the rm engine)
root.go # NewRoot(in,out,err) — builds the configured cobra command
execute.go # package cmd — Register(fs) + Execute() + buildOptions()
docs/ # Reference generator (cobra/doc: md/man/yaml/rest); tool-only dep
force/ # -f / --force
interactive/ # -i, -I, --interactive[=WHEN]
recursive/ # -r, -R, --recursive
directory/ # -d / --dir
verbose/ # -v / --verbose
onefilesystem/ # --one-file-system
preserveroot/ # --preserve-root / --no-preserve-root
version/ # --version
core/ # The removal engine
model.go # Options, Mode, Rm struct, injection points
core.go # New, Run, the walk, prompting, diagnostics, concurrency
permission_unix.go # writable()/deviceID() via syscall (build tag !windows)
permission_windows.go # writable()/deviceID() via os.FileInfo (build tag windows)
internal/
common/ # AppName + link-time Version
docmeta/ # zero-dep doc metadata type each cmd/<flag> exposes via Meta()
tools/gendocs/ # `go run ./tools/gendocs [dir] [format]` — reference generator
docs/ # Generated reference (committed, deterministic), grouped by format:
# <format>/{index.*, guide.*, flags/<flag>.*}
.github/workflows/ # go.yml (build+test matrix), lint.yml (gofmt/tidy + golangci-lint)
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.
- 1mo ago First seen · 232 lines · 3,116 tokens per session scan A 50f316d208a3
rmx AGENTS.md is an instructions file published in the GitHub repository braswelljr/rmx (5 stars, last pushed 2mo ago), licensed MIT. It adds 3,116 tokens to every session, about $0.0125 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.