The human-authored scope: concept-first, mid-level depth, CLI & manifests, HTML chapter subpages.
run-book dispatches agents in waves and tracks state on a shared to-do board.
Installs the apm CLI and prepares a scratch workspace so the real commands can be introspected and examples can run.
Wave 0: Design & scaffold
Turns the brief into toc.yml + outline.
Scaffolds the HTML shell + navigation.
Waves 1…N: per chapter group
Introspects the real apm CLI surface. No hallucinated commands.
Gathers concepts from the APM docs.
Fills the HTML slots and writes runnable example code.
Runs every example in a scratch project; each must exit 0 with no network.
Verdict: ACCEPT or REVISE with concrete fixes.
Each completed wave is committed, keeping a clean, auditable history.
Cross-chapter check of navigation, terminology, progression, and CLI/manifest consistency.
Verified chapters served as an interactive HTML site. Open it →
The actors (primitives)
🧭 Orchestrator prompt
The driver that runs the whole fleet in waves and tracks progress.
🏛️ Architect agent
Designs the table of contents and chapter outline from the brief.
📚 Theory researcher agent
Explains concepts grounded in the official APM documentation.
🔍 CLI explorer agent
Introspects the installed APM CLI for the exact, real command and manifest surface.
✍️ Chapter author agent
Writes chapter prose and example code into the page slots.
✅ Code verifier agent
Runs every example until it provably exits clean, with no network required.
🧐 Chapter reviewer agent
Critiques for accuracy and consistency; routes fixes back to the author.
🎨 Frontend builder agent
Scaffolds and finalizes the HTML shell, navigation, and styling.
⚙️ Environment setup skill
Reproducible recipe to install the APM CLI and prepare a scratch workspace.
🧱 Content & code rules instructions
Auto-applied conventions every chapter and example must follow.