Individual skill
ia-agent-native-architecture
Design agent-native applications where agents replace UI users as the primary actor. Use when designing MCP tools, agent-loop architectures, system prompt design, hooks policy, shared-workspace file patterns, or self-modifying agent systems.
plugins/whetstone/skills/ia-agent-native-architecture/SKILL.md
Source commit 5261531d15aea5e1a5f0b5a61af7c240bc17cf72
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 7, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 36
- Repository last updated
- Nov 8, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-agents Repository topic
- ai-tools Repository topic
- claude-code Repository topic
- claude-code-plugin Repository topic
- code-review Repository topic
- developer-tools Repository topic
- mcp-server Repository topic
- skills Repository topic
- design Derived category
- engineering Derived category
- design-interface Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 7,765 bytesSPEC.mddoc · 4,694 bytesreferences/action-parity-discipline.mddoc · 13,220 bytesreferences/agent-execution-patterns.mddoc · 21,601 bytesreferences/agent-native-testing.mddoc · 24,599 bytesreferences/anti-patterns.mddoc · 4,840 bytesreferences/architecture-patterns.mddoc · 20,898 bytesreferences/architecture-review-checklist.mddoc · 7,173 bytesreferences/cli-agent-interface.mddoc · 3,661 bytesreferences/core-principles.mddoc · 4,112 bytesreferences/durability-and-attestation.mddoc · 3,710 bytesreferences/dynamic-context-injection.mddoc · 16,716 bytesreferences/files-universal-interface.mddoc · 11,657 bytesreferences/from-primitives-to-domain-tools.mddoc · 11,787 bytesreferences/hooks-patterns.mddoc · 23,679 bytesreferences/intervention-evaluation.mddoc · 3,164 bytesreferences/mcp-tool-design.mddoc · 36,471 bytesreferences/mobile-cost.mddoc · 10,152 bytesreferences/mobile-execution.mddoc · 7,744 bytesreferences/mobile-patterns.mddoc · 10,719 bytesreferences/mobile-storage.mddoc · 8,147 bytesreferences/operator-approval-loop.mddoc · 3,005 bytesreferences/product-implications.mddoc · 13,264 bytesreferences/quick-start.mddoc · 1,382 bytesreferences/refactoring-to-prompt-native.mddoc · 9,350 bytesreferences/self-modification.mddoc · 10,947 bytesreferences/shared-workspace-architecture.mddoc · 21,417 bytesreferences/success-criteria.mddoc · 2,008 bytesreferences/system-prompt-design.mddoc · 8,066 bytes
Read excerpt
# 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](./references/core-principles.md).