Captures the decision to adopt @ai-hero/sandcastle as the orchestration
substrate for agent-driven development in this template. Records the
8-point decision (workspace dep, .sandcastle/ prompts, Dockerfile,
dispatch.mjs orchestrator, planning vs execute modes, generator-first
reviewer check, bring-your-own-key, per-task max-attempts), the four
alternatives considered (bare CLI / Copilot Workspace / custom-from-
scratch / no orchestrator), and four trade-offs (external dep, token
cost, Docker dependency, manual state mutation in v1).
Surfaces the decision at the top of README.md and AGENTS.md so new
contributors see the agent-driven framing before they hit the package
map or daily commands.
Adds a "Using Sandcastle for agent dispatch" section between the gate
table and Troubleshooting. Covers when to use / not use sandcastle,
prerequisites (Docker + agent API key + .sandcastle/ config), the
dispatch flow, a worked end-to-end example (plan → execute → review →
manual state mutation), troubleshooting (env vars, Docker, timeouts,
rejection modes), and a cost-aware planning-only variant.
10-task plan for standing up the conformance ESLint plugin in
@repo/core-eslint and shipping three structural rules:
- feature-must-have-manifest (warn): use-case files require a manifest
- usecase-must-have-test-file (error): TDD sibling test enforcement
- required-cores-installed (error): manifest cores ↔ workspace.yaml
Scope deliberately excludes manifest-AST analysis (no-undeclared-event-
publish, no-undeclared-audit) — those require parsing the manifest's TS
source as JS and walking the use-case AST, deferred to plan iii.b.
Uses regex-based manifest source extraction to avoid pulling in the
TypeScript compiler API at lint time. Manifest shape is constrained by
the literal `as const` form that defineFeature enforces, so the regex
path is sufficient.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
