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/code-yeongyu/codex-rules/rulesnpx skills add code-yeongyu/codex-rules --skill rulesgit clone --depth 1 https://github.com/code-yeongyu/codex-rulesWhat 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 | $0.00028 | $0.00283 |
| Opus 5 | $0.00014 | $0.00142 |
| Sonnet 5 | $0.00006 | $0.00057 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
rules 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.
This is a copy
89% identical to rules — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Codex Rules
Codex Rules is automatic once the plugin is enabled. It injects:
- static project instructions on
SessionStartandUserPromptSubmit - matching file-specific rules after Codex
apply_patchby default
Dynamic PostToolUse output is injected as additional context and is deduplicated per plugin data session. Codex Rules does not rewrite tool output.
Supported project sources:
AGENTS.mdCLAUDE.mdCONTEXT.md.sisyphus/rules/**/*.md.claude/rules/**/*.md.cursor/rules/**/*.md.github/instructions/**/*.md.github/copilot-instructions.md
Supported environment knobs:
CODEX_RULES_DISABLED=1CODEX_RULES_MODE=both|static|dynamic|offCODEX_RULES_MAX_RULE_CHARS=<number>CODEX_RULES_MAX_RESULT_CHARS=<number>CODEX_RULES_ENABLED_SOURCES=AGENTS.md,.sisyphus/rules
The legacy PI_RULES_* variables are accepted as fallbacks for users migrating from pi-rules.
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 · 35 lines · 28 tokens per session scan A 72a15e4e3516
rules is a skill published in the GitHub repository code-yeongyu/codex-rules (11 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 283 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to rules, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
codex-dsh-routing-suite
思维模式路由套件（dsh-routing-suite 的 Codex 移植版）操作手册。当任务涉及 路由/思维模式/路由器/devrouter/router/首轮锚定，或需要查看或切换当前会话的 spec/react/weak 模式、用不同模式派生一次性子进程、运行路由自检时使用。.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.