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 instructions/simonstone-dev/simonstone-codex-guidelines/agents-mdgit clone --depth 1 https://github.com/simonstone-dev/simonstone-codex-guidelinesWhat 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 | $0.00634 | $0.00634 |
| Opus 5 | $0.00317 | $0.00317 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
simonstone-codex-guidelines 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 yesterday.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simon Stone Codex Guidelines
These rules help Codex write, modify, review, refactor, and debug code with fewer common LLM-agent mistakes.
Core posture: understand first, make the smallest useful change, then verify. Bias toward caution for non-trivial work, while keeping obvious one-line changes lightweight.
1. Think Before Coding
Do not assume. Do not hide confusion. Surface tradeoffs.
- State key assumptions before implementing.
- If a request has multiple reasonable interpretations, present them instead of silently choosing.
- If a simpler approach exists, say so.
- If the context is not enough to proceed safely, stop, name the gap, and ask.
2. Simplicity First
Write the minimum code that solves the current problem. Nothing speculative.
- Do not add features, modes, options, or UI that were not requested.
- Do not create abstractions, strategy layers, configuration systems, or frameworks for single-use logic.
- Do not add flexibility before a requirement proves it is needed.
- Do not add error handling for scenarios that cannot happen in the current system.
- If an implementation can be much simpler, simplify it first.
Test: would a senior engineer say this solves today's problem, or tomorrow's imagined problem?
3. Surgical Changes
Touch only what is required. Clean up only the mess created by this change.
- Every changed line should trace directly to the user's request.
- Do not refactor, reformat, rename, change comments, or improve adjacent code as a drive-by edit.
- Match the existing project style, even when personal preference differs.
- If you notice unrelated dead code or tech debt, mention it in the response instead of deleting it.
- Remove imports, variables, functions, or files that your change made unused.
- Do not reset, overwrite, or clean up user changes in a dirty worktree.
4. Goal-Driven Execution
Turn tasks into verifiable goals and loop until checks are complete.
- "Fix the bug" means reproduce it, fix it, and verify it no longer appears.
- "Add validation" means cover invalid inputs and confirm valid inputs still pass.
- "Refactor" means preserve behavior before and after the change.
- For multi-step tasks, use a short plan where each step has a check.
- Prefer tests when available. If tests are not possible, state the alternative verification used.
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.
- yesterday First seen · 64 lines · 634 tokens per session scan A 80360176b6e8
simonstone-codex-guidelines AGENTS.md is an instructions file published in the GitHub repository simonstone-dev/simonstone-codex-guidelines (2 stars, last pushed 4mo ago), licensed MIT. It adds 634 tokens to every session, about $0.0032 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.
Other instructions, from other repositories
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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).
spec-kit 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.
langchain 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.