Build Foundry Ops to spec
Execute Foundry Ops build phases in order, picking todo tasks from TASKS.md and halting only when all phases complete or blockers surface.
# CLAUDE.md — Foundry Ops You are implementing Foundry Ops , the internal operating platform for Foundry Health (a ~12-person healthcare strategy consultancy, AU/NZ). This file is loaded into every Claude Code session. Read it at the start of every task. ## Read first, in this order 1. This file ( CLAUDE.md ) — conventions, guardrails, ralph-loop rules. 2. HANDOFF.md — the single source of truth for data model, roles, integrations, agents, and build order. When the HTML prototype and HANDOFF.md conflict, HANDOFF.md wins. 3. BUILD ORDER.md — the ordered phase plan. Don't jump phases. 4. TASKS.md — ralph-sized atomic tasks with acceptance criteria. Pick the first status: todo task. Never invent your own tasks — if something is missing, add it to TASKS.md and flag it, don't silently build it. 5. schema.prisma — canonical DB schema. The source of truth for entity shapes. 6. AGENTS.md — per-agent spec (receipt parser, AP intake, invoice drafter, contract drafter, AR chaser, timesheet reconciler, Xero reconciler). 7. INTEGRATIONS.md — per-integration spec (M365, Xero, pay.com.au, WhatsApp, DocuSign). 8. The HTML prototype ( Foundry Op
claude-code
More planning loops
loop-init, loop-audit, loop-cost CLI patterns
Three starter CLI tools that turn loop design into a repeatable workflow: scaffold a loop with a goal, budget, and verify step; audit an existing loop design; and estimate cost before you run.
Starter CLI tools: `loop-init` scaffolds a loop (goal, budget, verify step), `loop-audit` reviews an existing loop design, `loop-cost` estimates spend before running.
planningmedium risk
Run Ralph Loop toward persistent goals
Execute Plan-Act-Test-Review-Iterate cycles on a goal until it succeeds, pauses, blocks, or token budget exhausts.
/goal <objective — a persistent objective that survives sessions and runs the Ralph Loop (Plan → Act → Test → Review → Iterate) until the goal is achieved, paused, cleared, blocked ( unmet ), or the token budget is exhausted
planninghigh risk
Ralph the PRD backlog
The canonical Ralph loop: each iteration starts fresh, reads the PRD and guardrails, ships exactly one backlog item end-to-end, and records what it learned.
/loop start each iteration with fresh context: read PROMPT.md, prd.json, and .ralph/guardrails.md; pick the single highest-priority item in prd.json not marked done, implement it with tests, run the full check suite, commit and mark it done only if green; if blocked or a check fails twice the same way, append the lesson to .ralph/guardrails.md and move on; stop when every item is done or after 30 turns
planninghigh risk