A review process for applications where an agent takes actions for a user. It checks the app's tools, instructions, approvals, status signals, memory visibility, and ways for users to stop or correct the agent.

It is for auditing agent chats, tool-execution screens, agent settings, and dashboards, then producing a release-readiness decision and a summary of the user-agent relationship.

It helps find trust and safety problems before an agent-driven product is released. It focuses on agent interactions rather than ordinary forms, lists, or layout details.

ax-audit — Skill for Claude Code and Codex by HK-hub

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 HK-hub/AgentSkills --skill ax-audit

Clone the repo

git clone --depth 1 https://github.com/HK-hub/AgentSkills

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hk-hub/agentskills/ax-audit/github.svg)](https://agentmods.dev/skills/hk-hub/agentskills/ax-audit)

Your own site

<a href="https://agentmods.dev/skills/hk-hub/agentskills/ax-audit"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/ax-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hk-hub/agentskills/ax-audit"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/ax-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,148 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 88% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00113	$0.02148
Opus 5	$0.00056	$0.01074
Sonnet 5	$0.00023	$0.00430
Haiku 4.5	$0.00011	$0.00215

Measured 9d ago against content hash 473d740bb6f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ax-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 9d 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.

Origin

This is a copy

88% identical to ax-audit — 107 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

ax-audit/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AX Audit

Feature-level reviewer for apps where an agent acts for the user. One question: does it earn trust, and where does it break?

IS: rules-based audit of agentic surfaces (agent chat, tool execution panels, agent config, dashboards) across two layers (architecture in rules-arch/, trust/relationship design in rules-ax/), ending in a ship-readiness verdict plus an AX Relationship Summary.
IS NOT: traditional frontend UX (forms, states, focus, async, microcopy, accessibility, layout, typography, performance, use ui-audit); agent instruction-file quality (use agents-md).

No agentic features in scope (only forms, lists, modals)? Route to ui-audit; AX rules against traditional UI produce only noise.

Audit workflow
Two rule layers
Tiers and verdict
AX Relationship Summary
Reference files
Gotchas
Audit self-check
Related skills

Audit workflow

Track this checklist:

AX Audit progress:
- [ ] Step 1: Scope, via `git diff --name-only main` (PR mode) or explicit path (full sweep)
- [ ] Step 2: Detect agentic features per references/feature-playbooks.md
- [ ] Step 3: Run each detected feature's playbook in order, plus the diff-wide checks
- [ ] Step 4: For each check, load the rule file and follow its detection recipe
- [ ] Step 5: Tier each finding per references/ship-readiness.md (rule override table wins)
- [ ] Step 6: Render verdict + findings + AX Relationship Summary per references/output-format.md
- [ ] Step 7: Run the audit self-check and report its evidence counts

Step notes:

Scope. Default: PR diff plus the tool definitions and orchestrator code it touches. Findings in untouched files belong in a full sweep, not a PR verdict.
Detect. Heuristics (component names, hooks, routes) for the four feature types live in references/feature-playbooks.md.
Playbooks. Each feature has 5-9 ordered checks; run all, even expected passes (a pass with evidence belongs in the report). The diff-wide parity-orphan-ui-action runs on every PR-mode audit regardless of detected features.
Rules. Each rule file carries its own detection commands, false-positive guards, tier override table, and suppression syntax, and is authoritative; playbook annotations are a convenience copy.
Tier. Three tiers; precedence below.
Render. Group findings by surface; verdict block first, AX Relationship Summary last.
Self-check. Evidence or it didn't happen (see below).

Read the full file on GitHub · 126 lines

Files

What ships with it

32 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.

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.

9d ago First seen · 126 lines · 113 tokens per session scan A 473d740bb6f9

Subscribe to this mod's changes

ax-audit is a skill published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 22d ago), licensed MIT. It adds 113 tokens to every session and 2,148 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to ax-audit, differing in 107 lines, and is treated as a copy.

Building agents Claude Code Security agent-skills ai-agent mcp opencode prompt-engineering

ax-audit

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

AX Audit

Contents

Audit workflow

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

mermaid

teach-me

bootstrap

pr-stack

artifact-templates

deep-research