axiom-authority-auditor

axiom-authority-auditor is a skill for Claude Code, Codex from Zoverions/AXIOM-MESH. It costs 56 tokens per session (1,699 once invoked), scanned A, original, Apache-2.0.

A read-only checklist for deciding whether an agent is allowed to take a consequential action, such as changing files, using credentials, or sending messages. It checks identity, scope, consent, evidence, and whether permission can be withdrawn.

In plain words
What is it for?
Use it before actions involving repositories, databases, money, personal data, infrastructure, or external communication. It helps document why authority is or is not established.
Why use it?
It helps prevent an agent from treating technical ability, access, or possession of credentials as permission. It leaves the action to the governing policy or human decision-maker.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it before actions involving repositories, databases, money, personal data, infrastructure, or external communication. It helps document why authority is or is not established.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zoverions/axiom-mesh/axiom-authority-auditor
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 Zoverions/AXIOM-MESH --skill axiom-authority-auditor
Clone the repo
git clone --depth 1 https://github.com/Zoverions/AXIOM-MESH

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 axiom-authority-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/zoverions/axiom-mesh/axiom-authority-auditor/github.svg)](https://agentmods.dev/skills/zoverions/axiom-mesh/axiom-authority-auditor)
Your own site
<a href="https://agentmods.dev/skills/zoverions/axiom-mesh/axiom-authority-auditor"><img src="https://agentmods.dev/badge/skills/zoverions/axiom-mesh/axiom-authority-auditor/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 axiom-authority-auditor

Your own site · 80×15
<a href="https://agentmods.dev/skills/zoverions/axiom-mesh/axiom-authority-auditor"><img src="https://agentmods.dev/badge/skills/zoverions/axiom-mesh/axiom-authority-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,699 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 $0.00056 $0.01699
Opus 5 $0.00028 $0.00849
Sonnet 5 $0.00011 $0.00340
Haiku 4.5 $0.00006 $0.00170

Measured 12d ago against content hash 00ba9ec99043, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

axiom-authority-auditor 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 12d 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.

agent-skills/axiom-authority-auditor/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AXIOM Authority Auditor

Use this skill when an agent is considering a consequential action involving tools, APIs, files, repositories, databases, credentials, money, messages, infrastructure, personal data, other agents, or any external effect where the difference between can and may matters.

This skill is advisory only.

It does not:

  • execute the proposed action;
  • create authority;
  • expand an existing grant;
  • infer permission from capability, connectivity, credentials, or prior success;
  • substitute for the policy system that actually governs the environment;
  • certify AXIOM-MESH or any other runtime as secure;
  • decide moral legitimacy merely because authorization exists.

Core rule

Reachability, discovery, possession of credentials, and technical capability do not create authority on their own.

When required authority cannot be established for a consequential action, treat the authority state as not established. Do not upgrade uncertainty into permission.

Procedure

Before the action, build an Authority Assessment using the ten checks below.

1. Identity

Determine who or what would act.

Ask:

  • Is the actor's identity explicit?
  • Is the runtime or principal distinguishable from another actor?
  • Could the actor have been silently replaced, delegated, or proxied?
  • Is the identity relevant to the authority evidence actually bound to that identity?

If identity is ambiguous, authority is not established.

2. Capability

State what the actor can actually do.

Separate:

  • claimed capability;
  • demonstrated capability;
  • reachable resources;
  • available tools;
  • credentials or tokens currently present.

Do not treat any of these as permission.

3. Authority

Identify the exact basis for permission.

Record:

  • who granted it;
  • what action is permitted;
  • which resource or destination is covered;
  • scope and limits;
  • effective time and expiry;
  • whether the permission is still valid now;
  • whether enforcement exists outside the agent's own intention to comply.

Read the full file on GitHub · 262 lines

Files

What ships with it

1 file 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.

  1. 12d ago First seen · 262 lines · 56 tokens per session scan A 00ba9ec99043

Subscribe to this mod's changes

axiom-authority-auditor is a skill published in the GitHub repository Zoverions/AXIOM-MESH (2 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 1,699 once invoked, about $0.0003 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.