Generate payloads.

python3 scripts/payload_generator.py \
  --sheet ./my-agent/build-sheet.json --out-dir ./my-agent
# -> ./my-agent/payloads/{01-environment,02-agent,03-session,04-kickoff}.json

Agent toolset → always_allow; every MCP toolset → always_ask (baked into the agent payload's permission_policies).

Write the launch script.
```
python3 scripts/launch_script_writer.py --out-dir ./my-agent
```
launch.sh creates environment → agent → session → kickoff in order, chaining IDs, and resumes on re-run (each step skips if its *.id file exists). It reads $ANTHROPIC_API_KEY at runtime.
Validate before launch.
```
python3 scripts/payload_validator.py --dir ./my-agent
```
FAIL blocks — especially a key_leak finding. Fix and re-run.
Minimal key step (never in chat). Check the shell first:
```
[ -n "$ANTHROPIC_API_KEY" ] && echo "key present" || echo "export ANTHROPIC_API_KEY=... first"
```
Point the founder to platform.claude.com → API keys. Never print the key to chat, never write it to a file.
Launch + watch the first poll.
```
export ANTHROPIC_API_KEY=...      # in their shell, not in chat
./my-agent/launch.sh
```
Mark checkpoints with Console deep links. Then goal_state.py set --phase grade-iterate and advance.

Hard rules (API-key safety)

The key never enters chat, a file, a payload, or a log. launch.sh reads it from the environment; payload_validator.py scans for sk-ant-… leaks and FAILs.
Sequential launch. environment → agent → session → kickoff. Watch the first poll foreground before declaring success.
Resumable. Re-running launch.sh continues from the last created ID.

Forcing-question library (recommend + cite)

"Is the key in your shell env already?" Recommend: check $ANTHROPIC_API_KEY before anything. Cite: this SKILL, key-safety rules.
"Cloud or self-hosted environment?" Recommend: cloud for v0. Cite: cma-primitives.md (environment).
"Any MCP server in the payload?" Recommend: keep it always_ask. Cite: cma-primitives.md (permissions).
"Did the first poll return idle/running cleanly?" Recommend: watch it foreground before moving on. Cite: cma-primitives.md (session lifecycle).

Tools

scripts/payload_generator.py — build sheet → 4 ordered API payloads.
scripts/launch_script_writer.py — resumable BYOK curl launcher (no key handling).
scripts/payload_validator.py — pre-launch check + API-key-leak scan.

stage-launch

Phase 2 — Stage → Launch

Workflow