challenge-plans

# challenge-plans Harden a plan/spec in multi-agent adversarial review before execution, to reduce rework. Slots into `writing-plans → challenge-plans → executing-plans`. ## When to use (routing signals) - Input is a **single drafted artifact** + intent "review / find flaws / can this execute / harden / QA" → **use this skill**. Pick `--type` by what the artifact *is*: - a **spec / design doc / PRD** you're about to build → `--type spec` - **any plan with steps** to execute (dev or not — a trip, a launch, a hire) → `--type plan` - a **code change** (`git diff`) → `--type diff` - a **decision already made** (an ADR / "we chose X because Y" — a tech-stack pick, a vendor, a hire) → `--type decision`. Audits the *choice itself*: skipped alternatives, weak evidence, sunk-cost reasoning, irreversibility. - An agent has finished something and is **about to ask the user to decide or QA** → run this first and present the cross-review recommendation. - Input is **≥2 options still open to choose among** → use the sibling `weigh-options` (deliberation/voting), not this. (`--type decision` is the opposite: one option *already* chosen, audited after the fact.) ## Run ```bash # Installed from PyPI (pip install challenge-plans) — the console command is available directly. # Already installed but on an old version? update: pip install -U challenge-plans (pipx: pipx upgrade; uvx: append @latest). challenge-plans doctor # c...