Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.
Executor Abstraction
A reusable abstraction for running implementation work in an isolated workspace, independent of which agent host (Claude Code, Codex) or which mechanism is available. Lifecycle skills speak one vocabulary of operations; this skill maps each operation to a concrete recipe per mode. It is consumed as a library by /aep-launch, /aep-build, and /aep-autopilot, and can be invoked standalone to dry-run detection (see Standalone Usage).
Native-first: Claude Code launches use a native in-process background subagent (native-bg-subagent, the default) or — where the claude --bg flag exists — native background sessions (claude-bg); Codex launches use native subagents (codex-subagent) or headless exec workers (codex-exec). tmux+cmux is the `legacy` mode — selected only by explicit pin (git config aep.executor-backend tmux) or on generic hosts. Every mode runs its worker in an AEP-created git worktree at .feature-workspaces/<ws>.
How Other Skills Use This
| Skill | What it uses | Operations |
|---|---|---|
/aep-launch | Start the implementation agent + expose it for review | detect, spawn, present |
/aep-build Phase 5 | Spawn the evaluator in the right execution context | detect, spawn_evaluator |
/aep-build | Raise a human decision mid-build | gate |
/aep-autopilot | Run the periodic tick check cheaply; steer workspaces | detect, check, nudge, liveness, gate |
/aep-wrap | Tear down the worker + worktree after merge | teardown |
/aep-dispatch | Resolve the handoff mode; route "…with workflow" runs | detect |
The Operation Contract
Every consumer speaks these verbs. The recipe files supply the implementation per mode.
| Op | Purpose |
|---|---|
detect() | Resolve host + native capabilities + pin, select a mode |
spawn(ws, branch, prompt) | Start an implementation agent bound to the AEP worktree |
spawn_evaluator(ws, role) | Start an evaluator agent (worktree-bound) in the mode's eval context; accepts an optional tier-derived effort hint (see backends.md) |
nudge(ws, msg) | Send a mid-flight instruction (steerable modes; pull-based under claude-bg) |
liveness(ws) | Is the agent actively working? (mode-specific signal + git-diff corroboration) |
gate(ws) | Surface a worker's human decision: needs-human.md + the mode's transport, answered hub-and-spoke through the main agent (block-in-place or gate-and-park) |
check(prompt, schema) | Run a read-only analysis prompt in a cheap, context-isolated agent; return its JSON result — keeps a long-lived orchestrator session's context small |
monitor(ws) | Read .dev-workflow/signals/status.json — host-independent, never changes |
present(ws) | Human review surface (TaskOutput / claude attach / Codex thread / cmux tab / signals) |
teardown(ws) | Worker + worktree cleanup |
`monitor()` is already abstract. Progress is reported through signal files at phase boundaries regardless of the executor. Native push channels (SendMessage, send_input) are an acceleration layer — the signal files remain the durable, host-agnostic source of truth.
The Modes (summary)
| Mode | Lifetime | Selected when |
|---|---|---|
| native-bg-subagent | session-bound | Claude Code default + long-lived orchestrator |
| claude-bg | OS-bound | Claude Code, claude --bg present (cron driver / OS-bound need) |
| codex-subagent | session-bound | Codex with a living main thread (desktop app or interactive CLI) |
| codex-exec | OS-bound | Codex + cron driver, or hard isolation demanded |
| legacy | OS-bound | explicit pin (aep.executor-backend tmux), or generic host w/ tmux |
| workflow | session-bound | explicit opt-in ("…with workflow") + Claude Code (see /aep-workflow) |
| headless | session-bound | last resort |
Read references/backends.md for each mode's mechanism, the detection recipe, the full selection order, the driver × backend compatibility matrix, the human-gate protocol, and orphan re-adoption.
Reference Files
| File | Contents | When to read |
|---|---|---|
| `references/backends.md` | Mode matrix, detection, selection order, driver compatibility, gate protocol, orphan re-adoption, check() | Always, before spawning or steering |
| `references/claude-native.md` | native-bg-subagent (default) + claude-bg recipes, --bg availability note | When the selected mode is a Claude native one |
| `references/codex-native.md` | codex-subagent + codex-exec recipes, aep-builder/aep-evaluator role TOMLs, desktop app mapping | When the selected mode is a Codex one |
| `references/tmux-session.md` | legacy recipes (tmux spawn/nudge/liveness, cmux tab ladder) | When legacy is pinned or selected |
| `references/dogfood-validation.md` | dogfood_method() host × mode detection, e2e_tool(), target_url() resolution | When running dogfood validation (consumed by /aep-build, /aep-launch, /aep-watch, the autopilot post-merge guard) |
The skill also ships two probes, so the exact bash lives in one place instead of being retyped from a reference:
scripts/detect-backend.sh [--lifetime long|ephemeral] [--opt-in workflow|tmux] [--json]
— host, executor commands, native capabilities, pin, presentation surface, and the selected MODE. eval "$(bash scripts/detect-backend.sh)" to use it.
scripts/spawn-liveness-probe.sh <name> <agent_id>— the post-spawn liveness
probe every spawner runs (references/backends.md § Post-Spawn Liveness Probe).
Standalone Usage
Invoked directly, this skill reports what would happen:
- Run
bash scripts/detect-backend.sh(add--lifetime ephemeralwhen this
invocation is a cron/launchd one-shot — the script cannot probe that).
- Report each field it prints, and say why that
MODEwon: which earlier
rule in the selection order did not match.
- If the user asked "why not workflow / why not tmux", explain the opt-in/pin
gates.
This does not spawn anything — it is a dry-run of detect().
Rationale
Why native modes come first and tmux is a pinned legacy mode, why AEP owns the worktree, why session-bound vs OS-bound is a first-class axis, why human gates are hub-and-spoke, and why autopilot drives only steerable modes are recorded in docs/decisions/native-first-executor.md, docs/decisions/host-agnostic-executor.md, and docs/decisions/remove-claude-team.md.
Next Step
After detecting/spawning, control returns to the calling skill:
/aep-launch→ the bootstrap was the spawn prompt (native modes) or sent over
tmux (legacy), then /aep-build runs in the workspace
/aep-autopilot→ resumes its tick loop/aep-dispatch→ completes the handoff
