agent-native-audit

agent-native-audit is a skill for Claude Code, Codex from aegntic/compound-engineering. It costs 15 tokens per session (2,492 once invoked), scanned A, original, MIT.

A scored review of a codebase against principles for making software work well with AI agents. It examines how agents access features, app data, and user-visible actions.

In plain words
What is it for?
Use it after adding agent tools or prompts, before major agent-facing releases, or when checking whether agents can perform the same important tasks as users.
Why use it?
It replaces a general architecture opinion with a numeric baseline and a prioritized list of gaps. This makes agent-related improvements easier to compare and plan.

Skill for Claude CodeCodex

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.

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

Made for: Claude Code, Codex.

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/aegntic/compound-engineering/agent-native-audit.svg)](https://agentmods.dev/skills/aegntic/compound-engineering/agent-native-audit)
Your own site
<a href="https://agentmods.dev/skills/aegntic/compound-engineering/agent-native-audit"><img src="https://agentmods.dev/badge/skills/aegntic/compound-engineering/agent-native-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,492 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.02492
Opus 5 $0.00008 $0.01246
Sonnet 5 $0.00003 $0.00498
Haiku 4.5 $0.00002 $0.00249

Measured 3d ago against content hash f444c5c61cd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

skills/agent-native-audit/SKILL.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-Native Audit

Run a comprehensive review of a codebase against agent-native architecture principles, split the work into scored principle-specific audit tracks, and produce a prioritized summary report.

Announce at start: "I'm using the agent-native-audit skill to run a scored agent-native architecture review."

When to Use

  • After adding agent tools, prompts, commands, or shared-workspace behavior
  • Before shipping major agent-facing product changes
  • When you need a numeric baseline for how agent-native a system really is
  • When you want prioritized recommendations instead of a vague architectural opinion

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 important entity has full CRUD (Create, Read, Update, Delete)"
  6. UI Integration - "Agent actions are reflected in the product experience"
  7. Capability Discovery - "Users can discover what the agent can do"
  8. Prompt-Native Features - "Features are prompts defining outcomes, not rigid workflow code"

Workflow

Step 1: Load the Local Reference Skill

First, invoke agent-native-architecture to refresh the local vocabulary, principles, checklist, and anti-patterns used in this plugin.

Focus especially on:

  • Core principles
  • Architecture Review Checklist
  • Tool Design
  • Files & Workspace
  • Context Injection
  • UI Integration
  • Capability Discovery
  • Anti-Patterns

Use the local skill name directly. Do not rely on Every-specific namespaced invocations.

Step 2: Decide Audit Scope

If $ARGUMENTS names a single principle, audit only that principle.

Otherwise, audit all 8 principles.

When auditing a plugin, CLI, or developer-tooling codebase, map "user actions" and "UI" broadly:

Read the full file on GitHub · 365 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. 3d ago First seen · 365 lines · 15 tokens per session scan A f444c5c61cd8

Subscribe to this mod's changes

agent-native-audit is a skill published in the GitHub repository aegntic/compound-engineering (2 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 2,492 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

methodology

Analyzes captured HTTP traffic, designs the CLI architecture, and implements the Python CLI package (Phase 2): parse raw-traffic.json, identify the protocol, write api-spec.json, scaffold from templates, and implement endpoint methods and Click command groups. Use after a capture completes and raw-traffic.json exists.

ItamarZand88/CLI-Anything-WEB · 65 tokens

standards

Runs Phase 4 review/publish/verify for a cli-web- CLI: implementation review by 3 parallel agents, the tiered quality checklist (Tier 1 critical fail-fast, then comprehensive), pip install + smoke test, and per-CLI skill generation. Use when a CLI's tests pass and it is ready to be validated and published.

ItamarZand88/CLI-Anything-WEB · 73 tokens

testing

Writes and documents the test suite for a generated cli-web- CLI (Phase 3): unit tests with mocked HTTP, live E2E tests, subprocess tests via resolvecli, and the TEST.md plan/results record. Use after the methodology skill completes implementation.

ItamarZand88/CLI-Anything-WEB · 55 tokens

sync-check

Walks the documentation dependency web after a CLI code change and reports which downstream files (skills, SOPs, READMEs, plugin references) are out of sync. Use after fixing a bug, adding a command, changing auth behavior, refactoring, or before committing — and when the user says "sync check", "update docs"…

ItamarZand88/CLI-Anything-WEB · 95 tokens

boilerplate

Documents the template inventory and variable contract behind scaffold-cli.py — which Jinja2 template renders with which variables for each site profile. Use during Phase 2 scaffolding when choosing scaffold flags or understanding what the generated boilerplate contains. The scaffold-cli.py script is the primary path.

ItamarZand88/CLI-Anything-WEB · 60 tokens

futbin-cli

Queries FUTBIN (EA FC Ultimate Team database) via cli-web-futbin — player search, prices and price history, comparisons, SBCs, evolutions, and market analytics (index, trending, cheapest by rating, movers, fodder, buy/sell signals, undervalue scans, PS/PC arbitrage). Use when the user asks about EA FC player prices…

ItamarZand88/CLI-Anything-WEB · 116 tokens