agent-native-audit

agent-native-audit is a skill for Claude Code from marchatton/agent-skills. It costs 30 tokens per session (2,094 once invoked), scanned A, original, MIT.

A system-wide review process for checking whether an application follows principles for building software that AI agents can use and control.

In plain words
What is it for?
It helps audit a codebase across user actions, tools, context, shared data, CRUD operations, interface updates, and agent-oriented features.
Why use it?
It reveals gaps such as missing actions, incomplete data operations, weak state sharing, or features agents cannot discover or use.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

Good fit It helps audit a codebase across user actions, tools, context, shared data, CRUD operations, interface updates, and agent-oriented features.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marchatton/agent-skills/agent-native-audit
Install

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.

Any agent
npx skills add marchatton/agent-skills --skill agent-native-audit
Clone the repo
git clone --depth 1 https://github.com/marchatton/agent-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for agent-native-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/marchatton/agent-skills/agent-native-audit/github.svg)](https://agentmods.dev/skills/marchatton/agent-skills/agent-native-audit)
Your own site
<a href="https://agentmods.dev/skills/marchatton/agent-skills/agent-native-audit"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/agent-native-audit/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.

agentmods 80×15 button for agent-native-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/marchatton/agent-skills/agent-native-audit"><img src="https://agentmods.dev/badge/skills/marchatton/agent-skills/agent-native-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,094 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.02094
Opus 5 $0.00015 $0.01047
Sonnet 5 $0.00006 $0.00419
Haiku 4.5 $0.00003 $0.00209

Measured 7d ago against content hash b2af614e767d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-native-audit 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 7d 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.

.agents/skills/10-audit/agent-native-audit/SKILL.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-Native Architecture Audit

Conduct a comprehensive review of the codebase against agent-native architecture principles, running multi-agent slices (parallel or serial) and producing a scored report.

When to Use

  • System-wide health checks
  • Periodic audits
  • Major refactors or architecture resets

Output Location

  • Write results under docs/05-reviews-audits/ as agent-native-audit_YYYY_MM_DD.md.

Core Principles to Audit

  1. Action Parity - "Whatever the user can do, the agent can do"
  2. Tools as Primitives - "Tools provide capability, not behavior"
  3. Context Injection - "System prompt includes dynamic context about app state"
  4. Shared Workspace - "Agent and user work in the same data space"
  5. CRUD Completeness - "Every entity has full CRUD (Create, Read, Update, Delete)"
  6. UI Integration - "Agent actions immediately reflected in UI"
  7. Capability Discovery - "Users can discover what the agent can do"
  8. Prompt-Native Features - "Features are prompts defining outcomes, not code"

Workflow

Step 1: Load Skills

  1. Invoke the agent-native-architecture skill to understand all principles:
    /compound-engineering:agent-native-architecture
    
    Select option 7 (action parity) to load the full reference material.
  2. Run skill multi-agent-routing to decide sub-agents vs parallel/serial sessions.

Step 2: Run Agent Slices

Run 8 agent slices, one per principle.

  • If sub-agents are supported, launch them with the Task tool using subagent_type: Explore (parallel or serial per routing).
  • Otherwise open parallel sessions or run serially (one block per slice).

Each agent should:

  1. Enumerate ALL instances in the codebase (user actions, tools, contexts, data stores, etc.)
  2. Check compliance against the principle
  3. Provide a SPECIFIC SCORE like "X out of Y (percentage%)"
  4. List specific gaps and recommendations

Agent 1: Action Parity

Audit for ACTION PARITY - "Whatever the user can do, the agent can do."

Tasks:
1. Enumerate ALL user actions in frontend (API calls, button clicks, form submissions)
   - Search for API service files, fetch calls, form handlers
   - Check routes and components for user interactions
2. Check which have corresponding agent tools
   - Search for agent tool definitions
   - Map user actions to agent capabilities
3. Score: "Agent can do X out of Y user actions"

Format:
## Action Parity Audit
### User Actions Found
| Action | Location | Agent Tool | Status |
### Score: X/Y (percentage%)
### Missing Agent Tools
### Recommendations

Read the full file on GitHub · 290 lines

Changes

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.

  1. 7d ago First seen · 290 lines · 30 tokens per session scan A b2af614e767d

Subscribe to this mod's changes

agent-native-audit is a skill published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 2,094 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 2026-09-03.