/runtime-adapters
Use when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core. Use whenever a generated repo needs multiple AI runtimes without duplicating instructions.
$ npx -y skills add agentlas-ai/Agentlas-OS --skill runtime-adapters --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/runtime-adapters
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core. Use whenever a generated repo needs multiple AI runtimes without duplicating instructions.
SKILL.md
runtime-adapters.SKILL.mdname: runtime-adapters description: "Use when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core. Use whenever a generated repo needs multiple AI runtimes without duplicating instructions."
Runtime Adapters
Rules
- `AGENTS.md` is canonical.
- `.claude/`, `.codex/`, `.gemini/`, `.cursor/`, and root `skills/` are thin
adapters or mirrors.
- `.agentlas/global-commands.json` records the command each adapter exposes.
- Adapter text should point back to `AGENTS.md`.
- Do not claim identical behavior across runtimes. Say the canonical core is
portable and each adapter maps it into local conventions.
Required Adapters
- Codex: plugin manifest plus skill and `commands/<slug>.md`.
- Claude Code: command, agent, and skill adapter under `.claude/commands/`.
- Gemini CLI: `GEMINI.md` plus `.gemini/commands/<slug>.toml`.
- Generic: root `AGENTS.md` with the command alias documented.
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.
Other skills on agentlas-os.
- /agentlas-core-engine-meta-agent
Use when creating a single Agentlas agent, creating a multi-agent team, or packaging an existing local/external agent into Agentlas architecture. Make sure to use this for /meta-agent requests.
Open skill - /hephaestus-build
Use when the user types /prompts:hep-build, mentions @Hephaestus for build work, asks to create a single Agentlas agent, create a multi-agent team, or package an existing local/external agent into Agentlas architecture.
Open skill - /hephaestus-cloud
Use when the user types /hep-cloud or asks to staff from THEIR OWN Agentlas cloud packages only. Cloud is one exact source scope; Network means Local + owner Cloud + public Hub.
Open skill - /hephaestus-network
Use when the user types $hephaestus-network or /hep-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until
Open skill - /hephaestus-storm
Use when the user types /hep-storm, says @Hephaestus storm <goal>, or asks to drive a goal to verified completion through a force-robust Stormbreaker loop. Stormbreaker routes the goal to real Agentlas specialists, materializes a dependency-ordered pipeline fabric, and runs each
Open skill - /hephaestus-upload
Use when the user types $hephaestus-upload or /hep-upload, or asks to upload, publish, or list an Agentlas agent or team. Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate.
Open skill