メニュー
Create or revise native Codex execpolicy .rules files with narrow command prefixes, explicit decisions, and executable positive and negative examples. Use when governing shell-command approval behavior.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Start here for the nddev-builder toolkit. Indexes the Codex artifact families and the creator, checker, reviewer, and workflow skill that owns each, points at the single reference for schemas and current (Beta, experimental, or under-development) surfaces, and routes the task to the right skill. Use first whenever building, checking, reviewing, or releasing a Codex artifact, or when unsure which builder skill applies.
A guided first run of the nddev-builder toolkit — from zero to a working, checked Codex artifact in ordered steps. Use when new to nddev-builder, onboarding, or unsure which builder skill to start with.
Create or revise a Codex marketplace catalog with valid plugin sources, categories, installation policy, and authentication policy. Use when publishing local or remote plugin collections.
Check a managed Codex requirements.toml layer for supported keys, permission-profile consistency, and a valid lower-layer default. Use before delivering managed /etc/codex or MDM requirements.
Create a managed Codex requirements.toml layer that constrains permission profiles and other admin policy. Use when authoring the /etc/codex or MDM-delivered managed requirements a lower config layer must satisfy.
Install and iterate on a Codex plugin locally in developer mode: the install, reinstall, and cachebuster test loop for a plugin under development, run against an isolated install and never live state. Use when running or iterating on a plugin, its skills, MCP, hooks, or bundled app locally.
| name | codex-rule-creator |
| description | Create or revise native Codex execpolicy .rules files with narrow command prefixes, explicit decisions, and executable positive and negative examples. Use when governing shell-command approval behavior. |
Resolve every ../../scripts and ../../references path relative to this SKILL.md directory, never the caller working directory.
Create a minimal execpolicy rule that classifies one command family without granting unintended variants.
Define the exact command tokens, desired decision, trust rationale, platforms, and both allowed and disallowed examples.
Read ../../references/codex-artifact-contracts.md for the current rules language, locations, and evaluator behavior.
Inspect options and generate:
python3 ../../scripts/create_codex_artifact.py rule --help
python3 ../../scripts/create_codex_artifact.py rule --output .codex/rules --name safe-shell --description "Execpolicy for a bounded command family" --prefix git status
Use token-aware prefixes, not shell substrings. Prefer multiple narrow rules over one broad pattern.
Include justification and match examples where supported. Treat shell wrappers, flags, paths, and subcommands as separate attack surfaces.
Do not encode secrets, environment-specific home paths, or blanket allow rules.
Validate:
python3 ../../scripts/check_codex_artifact.py rule .codex/rules/safe-shell.rules
Run the native rules evaluator against positive, negative, wrapper, injection, and near-miss cases when available.