Borrowing it
Nothing to install: this file belongs to r3bl-org/r3bl-open-core. 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/r3bl-org/r3bl-open-core/main/AGENTS.mdgit clone --depth 1 https://github.com/r3bl-org/r3bl-open-coreWrote 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/r3bl-org/r3bl-open-core/agents-md)<a href="https://agentmods.dev/instructions/r3bl-org/r3bl-open-core/agents-md"><img src="https://agentmods.dev/badge/instructions/r3bl-org/r3bl-open-core/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/r3bl-org/r3bl-open-core/agents-md"><img src="https://agentmods.dev/badge/instructions/r3bl-org/r3bl-open-core/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 | $0.08514 | $0.08514 |
| Opus 5 | $0.04257 | $0.04257 |
| Sonnet 5 | $0.01703 | $0.01703 |
| Haiku 4.5 | $0.00851 | $0.00851 |
Grade C, and why
r3bl-open-core AGENTS.md scanned grade C with 3 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 3d 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 rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`sudo chown/chmod/rm` is forbidden. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
# Option B: Use the local store (if ~/.git-credentials is set up) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Recursive operations (`chown -R`, `chmod -R`, `rm -rf`) are STRICTLY PROHIBITED on the Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 709 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for r3bl-open-core
AI Agent Security & System Integrity Mandates
To prevent catastrophic system failures, all AI agents (Gemini, Claude, etc.) MUST adhere to these strict guardrails. These mandates take absolute precedence over any "YOLO" mode or perceived "fixes."
1. Critical Directory Protection
Recursive operations (chown -R, chmod -R, rm -rf) are STRICTLY PROHIBITED on the
following top-level system directories and their contents:
/(Root)/usr(System binaries and libraries)/etc(System configuration)/bin,/sbin,/lib,/lib64(Essential system paths)/boot(Bootloader and kernels)/var(Variable data, including system logs and databases)
2. Ownership & Integrity
- Root Ownership: System directories and binaries MUST remain owned by
root. The agent must NEVER suggest or execute a change of ownership for system-managed paths to a non-root user. - Privilege Escalation: Do not modify the
setuidorsetgidbits of any system binary (e.g.,sudo,pkexec,mount) unless specifically instructed by the user to fix a verified corruption.
3. Execution Safety
- Explicit Paths Only: All
sudocommands involving recursive changes or deletions MUST use absolute paths. The use of wildcards (*) or relative paths (.) withsudo chown/chmod/rmis forbidden. - Verification First: Before suggesting a permissions fix, the agent must first verify
the current state using
ls -ldorstat. - Destructive Warning: Any command that modifies system-wide permissions or ownership must be explicitly flagged to the user with a explanation of the risks, even in YOLO mode.
Ask for clarification immediately on important choices or ambiguities. Take your time with changes: slow, steady, and careful work beats fast and careless.
Standard Workflow (Alignment -> Plan -> Execute)
To ensure safety and alignment, always start by clarifying the scope of work. Ask the user: "Are we starting:
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.
- 3d ago Changed · +27 lines · +434 tokens per session d37c98b0ce32
- 9d ago First seen · 682 lines · 8,080 tokens per session scan C e7fc81dbd4d3
r3bl-open-core AGENTS.md is an instructions file published in the GitHub repository r3bl-org/r3bl-open-core (483 stars, last pushed 3d ago), licensed Apache-2.0. It adds 8,514 tokens to every session, about $0.0426 per session on Opus 5. A static security scan graded it C with 3 findings (asks for root, reaches for credential files, recursive force delete). 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.