rmx AGENTS.md

rmx AGENTS.md is an instructions file for Codex, OpenCode from braswelljr/rmx. It costs 3,116 tokens per session, scanned A, original, MIT.

Project instructions for rmx, a cross-platform replacement for the Unix rm command used to delete files and directories.

In plain words
What is it for?
Developing, testing, and extending rmx’s deletion engine and command-line options.
Why use it?
They describe how command-line flags, prompting, permissions, diagnostics, and concurrent removal should fit together without duplicating deletion logic.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/braswelljr/rmx/agents-md
Clone the repo
git clone --depth 1 https://github.com/braswelljr/rmx

Made for: Codex, OpenCode.

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.

agentmods badge for rmx AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/braswelljr/rmx/agents-md.svg)](https://agentmods.dev/instructions/braswelljr/rmx/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/braswelljr/rmx/agents-md"><img src="https://agentmods.dev/badge/instructions/braswelljr/rmx/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,116 This file is loaded in full into every session.
When invoked 3,116 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.03116 $0.03116
Opus 5 $0.01558 $0.01558
Sonnet 5 $0.00623 $0.00623
Haiku 4.5 $0.00312 $0.00312

Measured 4d ago against content hash 50f316d208a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

AGENTS.md · 232 lines

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 single core.Options. cmd/execute.go composes 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)

Read the full file on GitHub · 232 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.

  1. 4d ago First seen · 232 lines · 3,116 tokens per session scan A 50f316d208a3

Subscribe to this mod's changes

rmx AGENTS.md is an instructions file published in the GitHub repository braswelljr/rmx (5 stars, last pushed 15d ago), licensed MIT. It adds 3,116 tokens to every session, about $0.0156 per session on Opus 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.