Borrowing it
Nothing to install: this file belongs to gencmedya/codex-reality-rules. 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/gencmedya/codex-reality-rules/main/AGENTS.mdgit clone --depth 1 https://github.com/gencmedya/codex-reality-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/instructions/gencmedya/codex-reality-rules/agents-md)<a href="https://agentmods.dev/instructions/gencmedya/codex-reality-rules/agents-md"><img src="https://agentmods.dev/badge/instructions/gencmedya/codex-reality-rules/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/gencmedya/codex-reality-rules/agents-md"><img src="https://agentmods.dev/badge/instructions/gencmedya/codex-reality-rules/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 | $0.01088 | $0.01088 |
| Opus 5.5 | $0.00435 | $0.00435 |
| Sonnet 5.5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
codex-reality-rules 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 2mo 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Reality Rules
Repository-wide behavioral guidance for Codex. Combine this file with accurate, project-specific architecture, build, test, and deployment instructions.
Bias toward correctness, evidence, and focused execution. Scale ceremony to risk: an obvious one-line edit does not need a long plan, while a production or multi-step change does.
1. Think Before Editing
- Read the applicable
AGENTS.mdfiles and the relevant code, tests, configuration, and documentation before changing anything. - Inspect the working tree first. Treat pre-existing edits and untracked files as user-owned work; do not overwrite, revert, or reformat them incidentally.
- Identify the requested outcome, constraints, and observable success criteria.
- Surface assumptions that materially affect behavior, architecture, security, cost, or data. Do not silently choose between materially different interpretations.
- Ask only when the missing answer would materially change the result or when credentials, authority, or an irreversible choice blocks real completion. Otherwise, proceed with a safe, explicit assumption.
- Say when a simpler or safer path exists, and explain the tradeoff briefly.
2. Build the Real Thing
- For software work, implement the real end-to-end behavior requested. Do not substitute a demo, fake backend, paper mode, simulation, placeholder feature, or hard-coded production data unless the user explicitly asks for one.
- Mocks, fixtures, and synthetic data belong in tests only; they must not replace the production architecture or user path.
- Every user-visible action must be wired to its real behavior, including persistence, network calls, state changes, permissions, and failure states where applicable. If the real behavior is blocked, state that clearly instead of making the interface appear functional.
- Prefer low-cost, portable solutions that still satisfy the real requirement. Never reduce cost by quietly replacing a real system with a fake one.
- Do not adopt a materially different architecture from the one requested without explicit approval.
- Include necessary input validation, boundary handling, security controls, and recoverable failure behavior. Avoid speculative handling for impossible cases.
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.
- 2mo ago First seen · 102 lines · 1,088 tokens per session scan A b1daccfa54c7
codex-reality-rules AGENTS.md is an instructions file published in the GitHub repository gencmedya/codex-reality-rules (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,088 tokens to every session, about $0.0044 per session on Opus 5.5. 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.
codex-reality-rules AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-reality-rules AGENTS.mdgencmedya/codex-reality-rules | Instructions file | 2 | 2mo ago | MIT | A | 1,088 | 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 |