ai-coding-agents-settings-policy
Installation
SKILL.md
AI Coding Agents Settings Policy
Use this skill to design or review the settings and policy layer of a coding-agent runtime: settings sources, precedence, managed policy, validation, safe environment handling, runtime application of settings changes, and the fleet controls that decide which CLI version runs (release channel, version range, update kill switches, staged rollout).
This skill owns configuration and policy architecture for coding-agent runtimes. For project memory in AGENTS.md or CLAUDE.md, use ../agents-memory/SKILL.md.
Quick Reference
| Question | Read | Outcome |
|---|---|---|
| How should settings sources and policy precedence work? | references/settings-source-precedence-and-managed-policy.md | Source model, merge order, managed policy, plugin-only restrictions |
| How should settings be validated and applied safely? | references/settings-validation-and-safe-runtime-application.md | Schema validation, invalid-rule handling, safe env controls, runtime re-application |
| What are the exact override examples for each settings layer? | references/settings-precedence-table.md | Full precedence table: managed > CLI flags > local > project > user, with concrete examples and cache invalidation |
| Which sources can enable plugin surfaces? | references/plugin-only-restriction-recipes.md | Trust-class recipes for locking, scoping, and logging plugin-surface activations |
| How do I handle Codex “Exceeded skills context budget”? | references/openai-codex-managed-config-and-requirements.md#skill-catalog-context-budget | Supported budget override, safe config merge, rollback, and fresh-session verification |
| How do I enable Codex notes and searchable earlier context, including tool calls? | references/openai-codex-managed-config-and-requirements.md#notes-and-searchable-context-history | Experimental setting (look it up), memory distinction, and restart/validation steps |
| How do I pin the CLI version across a fleet, stop self-updates, or stage a CLI rollout? | references/managed-delivery-and-fleet-controls.md | Channel vs background check vs all-path block, hard range vs soft floor, fail-open or fail-closed per key class, install provenance, staged rollout |
| How does OpenAI Codex separate config layers from managed requirements? | references/openai-codex-managed-config-and-requirements.md | Layer stack, requirements constraints, managed-hooks-only mode, debug surfaces |