Connect Codex to the local AAS catalog, ask it to inspect your project and choose skills, then review a validated selection before installing anything. You do not need to copy the whole library into your project first.
The default Codex configuration is ~/.codex/config.toml. If you use a custom CODEX_HOME, set AAS_CONFIG to that directory’s absolute config.toml path instead.
These shell examples are for macOS and Linux. On native Windows, use PowerShell syntax, absolute Windows paths and the same preview/approval steps; see Windows setup. Do not paste bash variable assignments into PowerShell.
Set the paths and preview the proposed change. This creates the configuration parent directory if needed; the preview itself does not write the host configuration or install the managed runtime.
AAS_CONFIG="$HOME/.codex/config.toml"
AAS_CACHE="$HOME/.cache/aas"
AAS_BACKUP="$HOME/.aas-mcp-backups"
mkdir -p "$(dirname "$AAS_CONFIG")"
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@19.11.0 -- aas mcp configure \
--host codex --scope user --version 19.11.0 \
--config "$AAS_CONFIG" --cache-root "$AAS_CACHE" \
--backup-dir "$AAS_BACKUP"
Look for status: "approvalRequired", approvalDigest, the exact runtime version and the proposed managed aas section. Check that the configuration and cache paths are the ones you intended. The backup directory protects an existing configuration when you approve its replacement. If preview returns an error, resolve it before continuing.
Replace the placeholder with the preview’s actual approvalDigest, then run the same command with approval. Keep every other argument unchanged. If the preview becomes stale, preview again and review the new digest.
AAS_APPROVAL="PASTE_THE_PREVIEW_APPROVAL_DIGEST"
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@19.11.0 -- aas mcp configure \
--host codex --scope user --version 19.11.0 \
--config "$AAS_CONFIG" --cache-root "$AAS_CACHE" \
--backup-dir "$AAS_BACKUP" \
--approve "$AAS_APPROVAL"
Expect status: "configured" or "alreadyConfigured". Retain the returned runtime.integrity for the plan command below. AAS installs or verifies a content-addressed runtime and edits its managed MCP section; it preserves unrelated host settings and keeps a backup when replacing an existing file.
Run codex mcp get aas in your terminal, then open a fresh Codex session and run /mcp.
Confirm that aas connects and exposes search_skills, get_skill, compose_stack and inspect_stack. The terminal command shows configuration; a successful tool call in the client proves the connection. If aas is missing, check which configuration path the client uses and restart it. If it cannot connect, inspect its reported error rather than adding a second server entry.
Send this short connection check:
Use the local AAS MCP to search for systematic-debugging, then read that skill
with get_skill including its full content. Report its exact ID and catalog
version. Do not install anything or change project files.
You should receive actual tool results and the skill content. A directory existing on disk is not enough.
Give Codex your task and constraints, then paste this request:
Work autonomously. Inspect this project and identify its primary capability
areas. Evaluate architecture/runtime, languages/frameworks, domain behavior,
data/storage, integrations, testing/quality, security/privacy, user experience
and accessibility, deployment/operations, and maintenance; mark dimensions that
are not applicable. Search the complete AAS catalog for each applicable area,
paginate or refine the searches, and read and compare plausible candidates.
Choose non-redundant skill IDs that cover the applicable capabilities and report
catalog gaps. Do not optimize for the smallest stack. Use compose_stack with
these exact IDs, a project profile, and target codex:project to return a schema 2
manifest. Use inspect_stack and show me the result and selection rationale.
Do not install skills or write files yet.
Success means the agent has read real skills, returned aas-stack.json and obtained a valid inspection result. The agent chooses; Core checks IDs, structure and catalog identity. Validity does not establish semantic fit or safety to apply.
Review the exact IDs and requirements. Once you approve saving the selection, ask the agent to write the returned manifest unchanged to aas-stack.json in this project. MCP returns it in memory; the client saves it. Do not use a manifest from another release or substitute a sample manifest for the actual tool result.
In the same terminal, replace the integrity placeholder with runtime.integrity from step 2. AAS_PROJECT must be the absolute path to the existing project directory containing your reviewed manifest.
AAS_PROJECT="$PWD"
AAS_INTEGRITY="PASTE_RUNTIME_INTEGRITY_FROM_CONFIGURATION"
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@19.11.0 -- aas stack validate --manifest "$AAS_PROJECT/aas-stack.json"
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@19.11.0 -- aas stack plan \
--manifest "$AAS_PROJECT/aas-stack.json" \
--target codex:project --target-root "$AAS_PROJECT" \
--cache-root "$AAS_CACHE" --runtime-integrity "$AAS_INTEGRITY" \
--out "$AAS_PROJECT/aas-plan.json"
Run validation first and stop if it fails. Expect valid, then planned. Review aas-plan.json, or import it together with the manifest into Workbench. Planning writes only the requested plan artifact and leaves target skills unchanged. Core apply and recovery remain experimental.
Prepare the separate direct-installer dry run from the exact selected IDs:
npm exec --yes --ignore-scripts --package=agentic-awesome-skills@19.11.0 -- aas stack install-preview \
--manifest "$AAS_PROJECT/aas-stack.json" --cache-root "$AAS_CACHE" \
--destination "$AAS_PROJECT/.agents/skills"
This command returns an installation command; it does not execute it. Run the returned command with --dry-run, review the destination, release and selected IDs, then remove only --dry-run if you approve installation. The destination is this project’s .agents/skills directory. Keep the generated destination or choose the actual skill directory your client reads. The direct installer distributes complete skill bundles; it does not apply the Core plan.
Reopen the client if needed and ask it to use a selected skill on your original task. Check the resulting test, review or artifact. That is your first useful use, beyond merely producing a valid manifest.
The Core reference explains evidence exports, advanced configuration and trust boundaries. The direct library and plugin options below remain available when you already know which content you want.
Use a direct install only when you intentionally want the library copied into Codex’s skills path:
npx agentic-awesome-skills --codex
For plugin-style packaging, this repository also ships repo-local metadata in .agents/plugins/marketplace.json and plugins/agentic-awesome-skills/.codex-plugin/plugin.json.
It also generates bundle-specific Codex plugins so you can install a curated pack such as Essentials or Web Wizard as a marketplace plugin instead of loading the full library.
Those Codex plugins are plugin-safe filtered distributions. Skills that still depend on host-specific paths or undeclared setup stay in the repository, but are not published into the Codex plugin until they are hardened.
For the canonical explanation of how Core, Codex plugins, and direct installs relate, read plugins.md.
test -d .codex/skills || test -d ~/.codex/skills
brainstorming: clarify requirements before touching code.concise-planning: turn ambiguous work into an atomic execution plan.test-driven-development: structure changes around red-green-refactor.lint-and-validate: keep quality checks close to the implementation loop.create-pr: wrap up work cleanly once implementation is done.With AAS Core configured:
Inspect this parser project, search and read the complete AAS catalog, and choose the exact skill IDs you judge most useful for designing and testing the change. Use compose_stack with a project profile, show me the schema 2 aas-stack.json, inspect it, and preview the plan; do not apply it.
After installing or activating a chosen skill, direct invocation still works:
Use @concise-planning to break this feature request into an implementation checklist.
Use @test-driven-development to add tests before changing this parser.
Use @create-pr once everything is passing and summarize the user-facing changes.
aas-core.md for setup, trust boundaries, and the stack lifecycle.ai-agent-skills.md if you want a framework for choosing between broad and curated skill libraries.plugins.md if you want the plugin-specific install story for Codex and Claude Code.workflows.md when you want step-by-step execution patterns for common engineering goals.README.md for the full compatibility matrix.