Borrowing it
Nothing to install: this file belongs to EvilFreelancer/rpa-skills. 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/EvilFreelancer/rpa-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/EvilFreelancer/rpa-skillsWrote 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/evilfreelancer/rpa-skills/agents-md)<a href="https://agentmods.dev/instructions/evilfreelancer/rpa-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/evilfreelancer/rpa-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01867 | $0.01867 |
| Opus 5 | $0.00933 | $0.00933 |
| Sonnet 5 | $0.00373 | $0.00373 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
rpa-skills 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 8d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring & maintaining the rpa-skills catalog
Agent guide for working inside this aggregator repository. Read it before editing either marketplace manifest, the README Skills table, or the installer.
Naming (Russian): the adjective for "agent / agentic" is «агентный», never «агентский».
What this repo is
This repo is the catalog, not the skills. Each skill lives in its own repository
(EvilFreelancer/rpa-init, .../logika, …) and that repo is the single source of truth for the skill's
text, version, description, and tags. This catalog only points at those repos and re-states some of
their metadata so agents can discover and install them.
The same catalog is exposed to different agents through three surfaces:
rpa-skills/
├─ .claude-plugin/
│ └─ marketplace.json # Claude Code marketplace (per-plugin `version` + `description`)
├─ .agents/plugins/
│ └─ marketplace.json # Codex marketplace (git-backed sources; version resolved from the skill repo)
├─ install.sh # folder-based installer for Cursor & co. (ALL_SKILLS array of repo names)
├─ README.md # human overview + the Skills table (one row per skill)
├─ AGENTS.md # this file — the collection-wide process
├─ CLAUDE.md # symlink → AGENTS.md (so Claude Code reads the same guide)
└─ LICENSE
⚠️ Golden rule: the catalog mirrors the skills — keep them in sync
When you change a skill in its own repo — bump its version, reword its description, change its tags/category — this catalog keeps showing the old metadata until you update it here. The catalog follows, never leads: release in the skill repo first, then mirror the change here in the same PR/commit. Nothing is allowed to drift.
The catalog surface — every place a skill's metadata is duplicated
| Changed in the skill repo | Update here |
|---|---|
| version bump | .claude-plugin/marketplace.json → the plugin's version. Codex manifest only if its entry pins a ref/sha (see below). Always patch-bump the top-level metadata.version in both manifests (2.2.0 → 2.2.1). |
| description | description in both manifests and the README Skills-table row. |
| tags / category | category in both manifests. |
| new skill added | add an entry to both manifests, a README table row, the install.sh ALL_SKILLS array, and minor-bump metadata.version. |
| skill removed / renamed | remove or rename it in all four places above. |
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.
- 8d ago First seen · 124 lines · 1,867 tokens per session scan A e77868106bfc
rpa-skills AGENTS.md is an instructions file published in the GitHub repository EvilFreelancer/rpa-skills (35 stars, last pushed 26d ago), licensed MIT. It adds 1,867 tokens to every session, about $0.0093 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 2026-08-30.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.