Beau's rigorous agent workflow. beau-mode routes each task to a playbook and the principles; beau-help lists what the kit can do and what's new; skills for understanding (how, why, teach, recall), proof (verify-work, create- and maintain-verification-skill, create- and maintain-formal-verification-skill, swarm), design and planning (architect, arena, state-machines, technical-writing), product repos (scaffold-product and the Product phase playbook), review and trails (interrogate, show-me-your-work), and improvement (reflect, correct, unslop) do the steps. Adapted from Lauren Tan's pstack to work in any agent.
23 skills · 1 agent · hooks
A CFO for AI and cloud spending. Keeps a private cost ledger from receipts and provider billing data, separates cash cost from API-equivalent cost, estimates runs before they start, writes a weekly brief, and proposes budgets and cuts for you to approve. Never pays, cancels or deletes anything itself.
4 skills
Everyday engineering skills that work in any agent, for commit messages, cross-tool session handoffs, grilling a plan before you act on it, and sharpening a task to be deeper instead of bigger.
4 skills
Skills for engineering leaders, for design/RFC reviews and structured interview kits.
2 skills
Up-to-date library and API documentation lookup via the Context7 MCP server, with a no-MCP fallback.
1 skill · 1 MCP server
Twenty-four named engineering principles (prove it works, fix root causes, subtract before you add, build the lever, and more) that steer how agents design, build and verify, plus a benchmark checklist. One skill with one file per principle.
1 skill