Agent Workflow
Tillo Core should be legible to coding agents without hiding Laravel-specific correctness behind generic advice. The harness has three layers:
AGENTS.md/CLAUDE.mdare generated by Boost and injected into agent context. Do not edit them directly.docs/is the repository-local system of record.- Laravel Boost and
.ai/skills/provide executable, task-specific guidance.
Operating Model
Agents should gather only the context needed for the current task, then verify the result with the smallest relevant checks. If a rule or workflow is repeatedly needed, encode it where agents can discover and reuse it.
Use this sequence for most tasks:
- Read
docs/index.mdandARCHITECTURE.mdwhen the task touches unfamiliar territory. - Activate the relevant skill from
.ai/skills/. - Use Laravel Boost for Laravel framework behavior, Artisan commands, database inspection, tinker, browser logs, and version-specific documentation.
- Inspect sibling files before adding new structure.
- Make the smallest coherent change that satisfies the requested behavior.
- Run focused verification. When
ui/changed, runnix develop -c npm run format:allandnix develop -c npm run type:checkbefore finalizing (see.ai/guidelines/frontend-verification.md). - Update docs or skills only when the task changes durable project knowledge.
Laravel Boost Is Part Of The Harness
Laravel Boost is the Laravel-aware layer of this agent system. Do not replace Boost guidance with generic docs. Use Boost when:
- changing routing, middleware, validation, resources, policies, queues, migrations, or tests;
- confirming Laravel 12 behavior;
- checking Artisan command options before generation;
- inspecting schema or reading database state;
- debugging with tinker or browser logs.
Project docs should explain where Core-specific decisions live. Boost should remain the source for framework-version detail.
Knowledge Capture
Move hidden or repeated knowledge into the repository:
- Slack decisions that affect implementation become ADRs or module docs.
- Repeated PR comments become docs, tests, or lint rules.
- Debugging discoveries become focused troubleshooting entries.
- Complex rollout plans become versioned plans or ADRs when they will matter later.
Avoid one-off documentation churn. Capture knowledge when it will improve future agent or teammate decisions.