What is rskills AGENTS.md?

Instructions for rskills, a command-line tool that reads and searches remote agent skills without installing them. It can read files, list directory entries, and search available skills in interactive or structured output modes.

Reading a remote SKILL.md, listing a skill directory, searching skills, copying identifiers or install commands, and using structured command output.

They explain how to find the right skill and distinguish file reading from directory listing. This helps agents retrieve remote instructions in the format their workflow needs.

How fdarian/rskills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to fdarian/rskills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/fdarian/rskills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/fdarian/rskills

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/fdarian/rskills/agents-md/github.svg)](https://agentmods.dev/instructions/fdarian/rskills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/fdarian/rskills/agents-md"><img src="https://agentmods.dev/badge/instructions/fdarian/rskills/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/fdarian/rskills/agents-md"><img src="https://agentmods.dev/badge/instructions/fdarian/rskills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,881 This file is loaded in full into every session.

When invoked 3,881 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03881	$0.03881
Opus 5.5	$0.01552	$0.01552
Sonnet 5.5	$0.00776	$0.00776
Haiku 4.5	$0.00388	$0.00388

Measured 21d ago against content hash b97b1b210f8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

rskills AGENTS.md scanned grade B with 1 finding 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 21d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- `disableSkillShellExecution: true` in `<cwd>/.claude/settings.json` or `~/.claude/settings.json` turns commands into `[shell command execution disabled by policy]`.

AGENTS.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rskills

A Bun + Effect.ts CLI for reading remote skills without installing them. Built on incur for the CLI surface.

What it does

<source> is anything npx skills add <source> accepts (mirrors vercel-labs/skills src/source-parser.ts). A source may hold several skills; pick one with @skill or --skill, and a file inside it with --file.

rskills read <source>[@skill] [--skill <name>] [--file <path>] [--raw] — print a skill file (default SKILL.md) to stdout. Frontmatter is stripped; --raw returns the literal file, no envelope, in any --format. A directory --file exits non-zero with IsDirectory pointing to rskills ls.
rskills ls <source>[@skill] [--skill <name>] [--file <dir>] — structured { entries: [{ name, type }] } (mirrors Anthropic's ls/Glob: read is files-only, ls is directories). On a multi-skill source with no selector it lists the skill names as directory entries instead of erroring.
rskills lib add <source> [--skill <name>] [--tags a,b] [--note <text>] [--as <name>] / lib rm <name> / lib search [query] [--tags a,b] [--limit <n>] — a personal library of saved skill references (see Library). add returns the entry, rm { removed }, search { results }; lib search is never interactive.
rskills search [query] [--limit <n>] — skills.sh search only; results are { identifier, name, installs?, source } where identifier is owner/repo@skill or, for well-known sites, host.tld@skill; both feed straight into rskills read. skills.sh ids of any other shape are skipped, not fatal. On an interactive terminal (stdin + stdout both TTY, no --format/--json/--token-*) opens a live Ink picker: type to search (debounced 250 ms, race-safe via Effect fiber interruption), ↑/↓ to navigate, Enter for an action menu (read SKILL.md / copy identifier / copy install command / open on skills.sh / save to or remove from the library), Esc to quit. Otherwise emits structured output (TOON by default); query is required there.

Read the full file on GitHub · 159 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.

21d ago Changed · +14 lines · +779 tokens per session b97b1b210f8e
22d ago Changed · -62 lines · -901 tokens per session 0f4c32ff4dae
1mo ago Changed · +12 lines · +417 tokens per session 36534f11a784
2mo ago First seen · 195 lines · 3,586 tokens per session scan B 55db740e3f00

Subscribe to this mod's changes

rskills AGENTS.md is an instructions file published in the GitHub repository fdarian/rskills (2 stars, last pushed 22d ago), licensed Apache-2.0. It adds 3,881 tokens to every session, about $0.0155 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

rskills skills

rskills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rskills AGENTS.mdfdarian/rskills	Instructions file	2	22d ago	Apache-2.0	B	3,881	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

rskills: Instructions file for Codex