feat(spawn): generalise claude-handoff into agent-agnostic spawn skill

SKILL.md now only defines the handoff; per-agent launch mechanics
(claude --bg vs backgrounded codex exec) live in a bundled spawn.sh
the agent runs but never reads. Prompt arrives via heredoc/stdin so
long summaries with quotes survive.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

skills/in-progress/claude-handoff/SKILL.md

@@ -1,18 +0,0 @@
----
-name: claude-handoff
-description: Hand the current conversation off to a fresh background agent that picks up the work immediately.
-argument-hint: "What will the next session be used for?"
-disable-model-invocation: true
----
-
-Write a handoff summary of the current conversation so a fresh agent can continue the work. Instead of saving it, launch a background agent seeded with the summary as its prompt: `claude --bg --name "<descriptive name>" "<handoff summary>"`. It starts in the current working directory and returns immediately; the user manages it with `claude agents`.
-
-Always pass `-n`/`--name` with a descriptive name (e.g. `--name "Fix login bug"`) — it sets the display name shown in the job list, session picker, and terminal title.
-
-Include a "suggested skills" section in the summary, which suggests skills that the agent should invoke.
-
-Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
-
-Redact any sensitive information, such as API keys, passwords, or personally identifiable information — the summary becomes the agent's prompt.
-
-If the user passed arguments, treat them as a description of what the next session will focus on and tailor the summary accordingly.

skills/in-progress/claude-handoff/agents/openai.yaml

@@ -1,5 +0,0 @@
-interface:
-  display_name: "Claude Handoff"
-  short_description: "Hand off to a background agent"
-policy:
-  allow_implicit_invocation: false

skills/in-progress/spawn/SKILL.md

@@ -0,0 +1,23 @@
+---
+name: spawn
+description: Hand the current conversation off to a fresh background agent — claude or codex — that picks up the work immediately.
+argument-hint: "[claude|codex] What will the next session be used for?"
+disable-model-invocation: true
+---
+
+Write a handoff summary of the current conversation so a fresh agent can continue the work, then spawn the agent with it via the bundled [spawn.sh](spawn.sh) — run it, never read it:
+
+```bash
+bash <this skill's base directory>/spawn.sh <claude|codex> "<descriptive session name>" - <<'PROMPT'
+<handoff summary>
+PROMPT
+```
+
+Spawn `claude` unless the user named `codex`. The agent starts in the current working directory; the script prints how the user monitors the session — relay that.
+
+The handoff summary:
+
+- Include a "suggested skills" section naming skills the agent should invoke.
+- Reference artifacts (PRDs, plans, ADRs, issues, commits, diffs) by path or URL instead of duplicating them.
+- Redact sensitive information (API keys, passwords, PII) — the summary becomes the agent's prompt.
+- If the user passed arguments beyond the agent choice, treat them as what the next session will focus on and tailor the summary accordingly.

skills/in-progress/spawn/agents/openai.yaml

@@ -0,0 +1,5 @@
+interface:
+  display_name: "Spawn"
+  short_description: "Hand off to a background agent (claude or codex)"
+policy:
+  allow_implicit_invocation: false

skills/in-progress/spawn/spawn.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+# spawn.sh <claude|codex> <name> [prompt|-]
+# Launches a background agent session seeded with the prompt.
+# Prompt is read from stdin when the third argument is omitted or '-'.
+set -euo pipefail
+
+usage() {
+  echo "usage: spawn.sh <claude|codex> <name> [prompt|-]   (prompt read from stdin when omitted or '-')" >&2
+  exit 2
+}
+
+agent="${1:-}"
+name="${2:-}"
+prompt="${3:--}"
+[ -n "$agent" ] && [ -n "$name" ] || usage
+
+if [ "$prompt" = "-" ]; then
+  prompt="$(cat)"
+fi
+[ -n "$prompt" ] || { echo "spawn.sh: empty prompt" >&2; exit 2; }
+
+case "$agent" in
+claude)
+  claude --bg --name "$name" "$prompt"
+  echo "Spawned claude session '$name'. Manage it with: claude agents"
+  ;;
+codex)
+  slug="$(printf '%s' "$name" | tr '[:upper:] ' '[:lower:]-' | tr -cd 'a-z0-9-')"
+  dir="${TMPDIR:-/tmp}/codex-spawns"
+  mkdir -p "$dir"
+  base="$dir/${slug:-session}-$(date +%Y%m%d-%H%M%S)"
+  nohup codex exec --sandbox workspace-write --cd "$PWD" \
+    -o "$base.last.md" - <<<"$prompt" >"$base.log" 2>&1 &
+  echo "Spawned codex session '$name' (pid $!)."
+  echo "  log:          $base.log"
+  echo "  final answer: $base.last.md"
+  echo "  follow with:  tail -f $base.log"
+  ;;
+*)
+  usage
+  ;;
+esac