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.
npx agentmods add skills/roderik/ai-rules/rr-systemnpx skills add roderik/ai-rules --skill rr-systemgit clone --depth 1 https://github.com/roderik/ai-rulesWrote 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/skills/roderik/ai-rules/rr-system)<a href="https://agentmods.dev/skills/roderik/ai-rules/rr-system"><img src="https://agentmods.dev/badge/skills/roderik/ai-rules/rr-system.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 | $0.00000 | $0.03436 |
| Opus 5 | $0.00000 | $0.01718 |
| Sonnet 5 | $0.00000 | $0.00687 |
| Haiku 4.5 | $0.00000 | $0.00344 |
Grade C, and why
rr-system scanned grade C with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Enables Touch ID for sudo (macOS, requires sudo) Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Claude Code (`~/.claude/settings.json`) The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/ai-configs/AGENTS.md 15 KB
- assets/ai-configs/agents/quality-control.md 5.4 KB
- assets/ai-configs/agents/reviewer.md 6.2 KB
- assets/ai-configs/claude-mcp.json 310 B
- assets/ai-configs/claude-settings.json 1.9 KB
- assets/ai-configs/codex-config.toml 1.2 KB
- assets/ai-configs/command/create-pr.md 7.8 KB
- assets/ai-configs/command/fix-pr-comments.md 5.6 KB
- assets/ai-configs/command/update-docs.md 1.5 KB
- assets/ai-configs/cursor-settings.json 242 B
- assets/ai-configs/gemini-settings.json 675 B
- assets/ai-configs/opencode-config.json 7.1 KB
- assets/ai-configs/README.md 3.7 KB
- assets/Brewfile 2.9 KB
- assets/Brewfile.macos 1008 B
- assets/README.md 3.4 KB
- assets/shell-config/bash/.bash_profile 1.8 KB
- assets/shell-config/bash/.bashrc 264 B
- assets/shell-config/bash/.DS_Store 8.0 KB
- assets/shell-config/bash/conf.d/00-environment.bash 636 B runs code
- assets/shell-config/bash/conf.d/00-homebrew.bash 1.2 KB runs code
- assets/shell-config/bash/conf.d/02-paths.bash 564 B runs code
- assets/shell-config/bash/conf.d/10-aliases.bash 694 B runs code
- assets/shell-config/bash/conf.d/10-node.bash 396 B runs code
- assets/shell-config/bash/conf.d/11-1password.bash 561 B runs code
- assets/shell-config/bash/conf.d/12-ssh-agent.bash 354 B runs code
- assets/shell-config/bash/conf.d/13-gpg-agent.bash 142 B runs code
- assets/shell-config/bash/conf.d/20-functions.bash 1.6 KB runs code
- assets/shell-config/bash/conf.d/20-fzf.bash 1015 B runs code
- assets/shell-config/bash/conf.d/30-abbreviations.bash 1.7 KB runs code
- assets/shell-config/bash/conf.d/30-git-functions.bash 2.4 KB runs code
- assets/shell-config/bash/conf.d/31-docker-functions.bash 560 B runs code
- assets/shell-config/bash/conf.d/32-claude-function.bash 892 B runs code
- assets/shell-config/bash/conf.d/40-completions.bash 149 B runs code
- assets/shell-config/bash/conf.d/60-modern-tools.bash 939 B runs code
- assets/shell-config/bash/conf.d/70-prompt.bash 622 B runs code
- assets/shell-config/bash/conf.d/80-gcloud.bash 841 B runs code
- assets/shell-config/bash/conf.d/81-aws.bash 180 B runs code
- assets/shell-config/bash/conf.d/82-azure.bash 399 B runs code
- assets/shell-config/bash/conf.d/83-kubectl.bash 1.2 KB runs code
- assets/shell-config/bash/conf.d/84-tmux.bash 338 B runs code
- assets/shell-config/bash/conf.d/85-uv.bash 869 B runs code
- assets/shell-config/bash/conf.d/86-additional-tools.bash 2.0 KB runs code
- assets/shell-config/bash/conf.d/86-grc.bash 988 B runs code
- assets/shell-config/bash/conf.d/87-foundry.bash 611 B runs code
- assets/shell-config/bash/conf.d/README.md 1.4 KB
- assets/shell-config/fish/conf.d/00-environment.fish 1.8 KB
- assets/shell-config/fish/conf.d/00-homebrew.fish 1.2 KB
- assets/shell-config/fish/conf.d/02-paths.fish 608 B
- assets/shell-config/fish/conf.d/05-fish4-features.fish 3.2 KB
- assets/shell-config/fish/conf.d/10-aliases.fish 1.1 KB
- assets/shell-config/fish/conf.d/10-node.fish 423 B
- assets/shell-config/fish/conf.d/11-1password.fish 882 B
- assets/shell-config/fish/conf.d/12-ssh-agent.fish 364 B
- assets/shell-config/fish/conf.d/13-gpg-agent.fish 106 B
- assets/shell-config/fish/conf.d/20-functions.fish 2.7 KB
- assets/shell-config/fish/conf.d/20-fzf.fish 880 B
- assets/shell-config/fish/conf.d/30-abbreviations.fish 2.1 KB
- assets/shell-config/fish/conf.d/30-git-functions.fish 2.6 KB
- assets/shell-config/fish/conf.d/31-docker-functions.fish 568 B
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.
- 4d ago First seen · 487 lines · 0 tokens per session scan C 603177f1029d
rr-system is a skill published in the GitHub repository roderik/ai-rules (53 stars, last pushed 1mo ago), with no licence file. It costs nothing until one of its globs matches a file; then it loads 3,436 tokens. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
auth-web-cloudbase
CloudBase Web Authentication Quick Guide for frontend integration after auth-tool has already been checked. Provides concise and practical Web authentication solutions with multiple login methods and complete user management.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…