Agent-Native Architecture#

Working rules#

• Keep authority, scope, approval, and runtime isolation in trusted orchestration; prompts alone cannot enforce them.
• Provide explicit completion and partial-progress signals, durable state, and observable action results.
• Validate capabilities with real tasks, including failure and interruption paths; do not infer improvement from elapsed usage.
• Evaluate discovery from original inputs. Replaying fixed candidates measures classification and cannot reveal candidates a changed search would miss or invent. Compare each discovery variant with a fresh baseline on the same complete inputs in isolation. Independently adjudicate unmatched outputs from the complete result sets, including outputs from clean tasks.
• Calibrate decision gates per model. A replacement model's confidence scores do not preserve the previous model's cutoff, even when ranking accuracy improves. Fit thresholds on a separate calibration set. Verify false-positive and false-negative behavior through the production decision path on untouched representative cases.
• Use the selected topic's references and the architecture checklist to produce a concrete design with evidence and unresolved constraints.

Core Principles#

Five principles govern agent-native design. For detailed explanations, examples, and test criteria, see core-principles.md.

PrincipleOne-line testParityCan the agent achieve every outcome the UI allows?GranularityChanging behavior means editing prose, not refactoring codeComposabilityCan a feature be added by writing a new prompt, without new code?Emergent CapabilityCan the agent handle open-ended requests it wasn't designed for?Improvement Over TimeDoes the app work better after a month, even without code changes?

Focus Area Selection#

1. Design architecture - Plan a new agent-native system from scratch
2. Files & workspace - Use files as the universal interface, shared workspace patterns
3. Tool design - Build primitive tools, dynamic capability discovery, CRUD completeness
4. Domain tools - Know when to add domain tools vs stay with primitives
5. Execution patterns - Completion signals, partial completion, context limits
6. System prompts - Define agent behavior in prompts, judgment criteria
7. Context injection - Inject runtime app state into agent prompts
8. Action parity - Ensure agents can do everything users can do
9. Self-modification - Enable agents to safely evolve themselves
10. Product design - Progressive disclosure, latent demand, approval patterns
11. Mobile patterns - iOS storage, background execution, checkpoint/resume
12. Testing - Test agent-native apps for capability and parity
13. Refactoring - Make existing code more agent-native
14. Anti-patterns - Common mistakes and how to avoid them
15. Success criteria - Verify your architecture is agent-native
16. Hooks patterns - Hook events, decision control, MCP matchers, async hooks
17. CLI interface - Design a CLI that agents invoke: output channels, exit codes, self-description, safety tiers
18. Approval loop - Durable human approval for agent-drafted external sends: content binding, single-winner claim, unknown outcomes

Route directly when the request or delegated task identifies the topic. When a material focus remains unresolved, present the relevant options using AskUserQuestion in Claude Code (load it with ToolSearch if needed), request_user_input in Codex, or numbered options in chat when no question tool is available. Wait only for the answer needed to resolve that choice.

Reference Routing#

ResponseAction1, "design", "architecture", "plan"Read architecture-patterns.md, then apply architecture-review-checklist.md2, "files", "workspace", "filesystem"Read files-universal-interface.md and shared-workspace-architecture.md3, "tool", "mcp", "primitive", "crud"Read mcp-tool-design.md4, "domain tool", "when to add"Read from-primitives-to-domain-tools.md5, "execution", "completion", "loop"Read agent-execution-patterns.md6, "prompt", "system prompt", "behavior"Read system-prompt-design.md7, "context", "inject", "runtime", "dynamic"Read dynamic-context-injection.md8, "parity", "ui action", "capability map"Read action-parity-discipline.md9, "self-modify", "evolve", "git"Read self-modification.md10, "product", "progressive", "approval", "latent demand"Read product-implications.md11, "mobile", "ios", "android", "background", "checkpoint"Read mobile-patterns.md11a, "icloud", "storage", "documents", "file state", "entitlement"Read mobile-storage.md11b, "background task", "battery", "on-device", "cloud routing"Read mobile-execution.md11c, "model tier", "token budget", "cost-aware", "batch", "caching"Read mobile-cost.md12, "test", "testing", "verify", "validate"Read agent-native-testing.md13, "review", "refactor", "existing"Read refactoring-to-prompt-native.md14, "anti-pattern", "mistake", "wrong"Read anti-patterns.md15, "success", "criteria", "verify", "checklist"Read success-criteria.md16, "hook", "hooks", "PreToolUse", "decision control", "async hook", "permissionDecision"Read hooks-patterns.md17, "cli", "command line", "stdout", "exit code", "--format", "--dry-run"Read cli-agent-interface.md18, "approval", "approve before send", "outbound", "ledger", "double-send"Read operator-approval-loop.md0, "quick start", "getting started", "overview", "introduction"Read quick-start.md

After reading the reference, apply those patterns to the user's specific context.

Task-specific references#

Read the relevant reference before implementing or reviewing the matching behavior:

• Before implementing an agent-native architecture, address every applicable architecture checklist item: architecture-review-checklist.md.

Existing specialized references, when the corresponding topic applies:

• durability-and-attestation.md.
• For controlled evaluations of hooks, skills, or prompt rules, read intervention-evaluation.md.