Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add iliaal/ai-skills --skill agent-native-architecturegit clone --depth 1 https://github.com/iliaal/ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/iliaal/ai-skills/agent-native-architecture)<a href="https://agentmods.dev/skills/iliaal/ai-skills/agent-native-architecture"><img src="https://agentmods.dev/badge/skills/iliaal/ai-skills/agent-native-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/iliaal/ai-skills/agent-native-architecture"><img src="https://agentmods.dev/badge/skills/iliaal/ai-skills/agent-native-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 7 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 58 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.01423 |
| Opus 5 | $0.00024 | $0.00711 |
| Sonnet 5 | $0.00010 | $0.00285 |
| Haiku 4.5 | $0.00005 | $0.00142 |
Grade A, and why
agent-native-architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- ia-agent-native-architecture — 91% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
- 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.
| Principle | One-line test |
|---|---|
| Parity | Can the agent achieve every outcome the UI allows? |
| Granularity | Changing behavior means editing prose, not refactoring code |
| Composability | Can a feature be added by writing a new prompt, without new code? |
| Emergent Capability | Can the agent handle open-ended requests it wasn't designed for? |
| Improvement Over Time | Does the app work better after a month, even without code changes? |
Focus Area Selection
- Design architecture - Plan a new agent-native system from scratch
- Files & workspace - Use files as the universal interface, shared workspace patterns
- Tool design - Build primitive tools, dynamic capability discovery, CRUD completeness
- Domain tools - Know when to add domain tools vs stay with primitives
- Execution patterns - Completion signals, partial completion, context limits
- System prompts - Define agent behavior in prompts, judgment criteria
- Context injection - Inject runtime app state into agent prompts
- Action parity - Ensure agents can do everything users can do
- Self-modification - Enable agents to safely evolve themselves
- Product design - Progressive disclosure, latent demand, approval patterns
- Mobile patterns - iOS storage, background execution, checkpoint/resume
- Testing - Test agent-native apps for capability and parity
- Refactoring - Make existing code more agent-native
- Anti-patterns - Common mistakes and how to avoid them
- Success criteria - Verify your architecture is agent-native
- Hooks patterns - Hook events, decision control, MCP matchers, async hooks
What ships with it
25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/action-parity-discipline.md 11 KB
- references/agent-execution-patterns.md 13 KB
- references/agent-native-testing.md 16 KB
- references/anti-patterns.md 4.4 KB
- references/architecture-patterns.md 17 KB
- references/architecture-review-checklist.md 7.3 KB
- references/core-principles.md 4.0 KB
- references/durability-and-attestation.md 2.9 KB
- references/dynamic-context-injection.md 13 KB
- references/files-universal-interface.md 9.8 KB
- references/from-primitives-to-domain-tools.md 12 KB
- references/hooks-patterns.md 9.0 KB
- references/mcp-tool-design.md 22 KB
- references/mobile-cost.md 5.1 KB
- references/mobile-execution.md 7.2 KB
- references/mobile-patterns.md 8.8 KB
- references/mobile-storage.md 4.7 KB
- references/product-implications.md 13 KB
- references/quick-start.md 1002 B
- references/refactoring-to-prompt-native.md 9.1 KB
- references/self-modification.md 8.9 KB
- references/shared-workspace-architecture.md 20 KB
- references/success-criteria.md 1.8 KB
- references/system-prompt-design.md 6.5 KB
- SPEC.md 4.6 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed · -41 lines 9077606b71fc
- 3d ago Changed 6f8f86ec0817
- 11d ago First seen · 133 lines · 49 tokens per session scan A 0ddaae366f5d
agent-native-architecture is a skill published in the GitHub repository iliaal/ai-skills (41 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 1,423 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.
gpt-vis
A chart-generation tool that recommends visual formats for data and produces either chart settings or runnable code. It uses GPT-Vis, a library for rendering data visualisations.
infographic-creator
Create beautiful infographics based on given text content. Use when users request to create infographics.
icon-retrieval
Search icons through HTTP API and retrieve SVG strings with curl.
pneuma-bansho
A board-based way to explain ideas through written Markdown, a simple text-formatting language, with the writing appearing progressively like a live lecture.
review-spd
Findings-first code review workflow for AI coding agents. Use when the user asks to review uncommitted changes, commits in a date range, or a branch compared to the main branch / PR-style diff. Focuses on bugs, regressions, correctness risks, missing tests, security/data-safety issues, and other behavior-changing…