Plugin

strategy-pack

Two read-only Claude Code subagents designed for solo founders and small teams whose strategy lives in distributed markdown docs. **/business-critic** — daily devil's-advocate. Reads your BUSINESS.md, ROADMAP.md, and recent session log; does live web search for competitor moves and industry news; produces a critique where every doubt cites a URL or a falsifiable experiment. Rotates through seven critique dimensions (positioning, activation gates, monetization, competitive substitution, GTM, founder reality, strategic drift), going deep on three or four per run. No cheerleading. **/pm** — weekly cross-document alignment auditor. Scans BUSINESS.md, ROADMAP.md, every backlog (todo-*.md / BACKLOG-*.md), in-flight plan files, API contract docs, and git log. Flags orphaned commitments ("ROADMAP promised X, no owning task"), blocked-by mismatches across domains, stale plans, and API doc lag. Drafts follow-up plan stubs without ever editing your docs. Both agents are strictly read-only — they produce reports you act on. Pair them: daily critic for external skepticism, weekly auditor for internal coordination.

• Published source
• Repository

Analysed

11 October 2026

Last observed

11 October 2026

What the code does

Static analysis found none of the capabilities we track, such as shell commands, network requests or file writes, in the latest version.

Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.

This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.