arbiterx AGENTS.md

Coding rules for AI-generated software, including guidance to write only necessary code, handle errors, and avoid unsafe practices.

In plain words
What is it for?
Use it to guide code generation and review in projects where functions, inputs, resources, secrets, network calls, and database queries need consistent rules.
Why use it?
It reduces unnecessary abstractions, unfinished work, hidden errors, and common security risks in generated code.

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/neelprime/arbiterx/agents-md
Clone the repo
git clone --depth 1 https://github.com/NeelPrime/arbiterx

Made for: Codex, OpenCode.

Per session 345 This file is loaded in full into every session.
When invoked 345 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 $0.00345 $0.00345
Opus 5 $0.00172 $0.00172
Sonnet 5 $0.00069 $0.00069
Haiku 4.5 $0.00034 $0.00034

Measured 2d ago against content hash 520c4f5a6ff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arbiterx 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 2d 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 · 41 lines

What it actually says

ArbiterX — Engineering Discipline for AI Code Generation

Before Writing Code

Run this ladder. Stop at the first "yes":

  1. Does this need to exist? → No → skip (YAGNI)
  2. Already in this codebase? → Reuse it
  3. Stdlib does it? → Use stdlib
  4. Installed dep does it? → Use it
  5. One-liner? → One line, no abstraction
  6. Only then → write the minimum that works

The 10 Rules (Always Enforce)

  1. Type all function signatures (params + return)
  2. Handle every error path (no bare except, no swallowed errors)
  3. Close every resource (use with, never bare open)
  4. Name all constants (no magic numbers)
  5. One function = one job (max 30 lines)
  6. Validate inputs at function entry
  7. No dead code (no commented code, no unused imports)
  8. Finish everything (no TODO/FIXME — implement or skip)
  9. Prefer immutable (frozen dataclasses, tuples)
  10. Every line earns its place (delete what doesn't change behavior)

Never Generate

  • Hardcoded secrets (API keys, passwords, tokens)
  • SQL with string formatting (use parameterized queries)
  • eval() or exec()
  • subprocess with shell=True
  • Network calls without timeouts
  • File ops without error handling

After Writing

  • Can any line be deleted without breaking behavior? → Delete it
  • Is there a simpler stdlib approach? → Use it
  • Would this pass review by the strictest engineer you know? → If not, fix it
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. 2d ago First seen · 41 lines · 345 tokens per session scan A 520c4f5a6ff9

Subscribe to this mod's changes

arbiterx AGENTS.md is an instructions file published in the GitHub repository NeelPrime/arbiterx (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 345 tokens to every session, about $0.0017 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.