neura-authority-review

neura-authority-review is a skill for Claude Code, Codex from neurarelay/relay-action-card. It costs 44 tokens per session (282 once invoked), scanned A, original, MIT.

A review checklist for deciding whether an agent action has the right identity, permission, evidence, and safety requirements.

In plain words
What is it for?
Use it to review pull requests, scripts, workflows, automations, and other proposed actions before execution.
Why use it?
It exposes missing authority or risk information before an agent runs an action, such as a deployment, data export, or customer communication.

Skill for Claude CodeCodex

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

Good fit Use it to review pull requests, scripts, workflows, automations, and other proposed actions before execution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/neurarelay/relay-action-card/neura-authority-review
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 neurarelay/relay-action-card --skill neura-authority-review
Clone the repo
git clone --depth 1 https://github.com/neurarelay/relay-action-card

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 neura-authority-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/neurarelay/relay-action-card/neura-authority-review/github.svg)](https://agentmods.dev/skills/neurarelay/relay-action-card/neura-authority-review)
Your own site
<a href="https://agentmods.dev/skills/neurarelay/relay-action-card/neura-authority-review"><img src="https://agentmods.dev/badge/skills/neurarelay/relay-action-card/neura-authority-review/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 neura-authority-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/neurarelay/relay-action-card/neura-authority-review"><img src="https://agentmods.dev/badge/skills/neurarelay/relay-action-card/neura-authority-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 282 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 $0.00044 $0.00282
Opus 5 $0.00022 $0.00141
Sonnet 5 $0.00009 $0.00056
Haiku 4.5 $0.00004 $0.00028

Measured 12d ago against content hash 119df42c0081, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

neura-authority-review 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.

skills/neura-authority-review/SKILL.md · 19 lines

What it actually says

Neura Authority Review

Use this skill to inspect a proposed action before execution. Map the action to the Authority Decision Engine v0.1 proof, then recommend whether the developer should request a Relay Decision Receipt before downstream execution. Do not claim the full engine is complete.

Workflow

  1. Identify the acting agent, owner, capability, version, proposed action, target resource, and affected object.
  2. Check authority path: delegated-by ref, acting-agent ref, allowed action, allowed resource, expiry, revocation, changed-since-issue, authority scope ref, standing ref, and Registry-backed source when available.
  3. Classify action risk by consequence: money, legal commitment, customer communication, production infrastructure, data/privacy, permissions/security, cross-tenant scope, reversibility, and blast radius.
  4. List missing requirements and route: proceed, revise, human_review, or stop.
  5. Keep output refs-only. Do not expose private payloads, secrets, token values, or raw policy/customer data.

Use references/authority-decision-checklist.md when a more detailed review is needed.

Files

What ships with it

2 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.

  1. 12d ago First seen · 19 lines · 44 tokens per session scan A 119df42c0081

Subscribe to this mod's changes

neura-authority-review is a skill published in the GitHub repository neurarelay/relay-action-card (2 stars, last pushed 20d ago), licensed MIT. It adds 44 tokens to every session and 282 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 2026-08-31.

Related

Other skills, from other repositories

loom-integrations

Configure and verify CodexLoom external platform integrations with the loom CLI. Use when inspecting or changing Connections, Agent Addresses, DM access, group/channel Conversation Memberships, trigger and reply policies, allow/block rules, trust domains, or Inbox/Outbox delivery for Feishu/Lark, Slack, Parall, and…

yan5xu/codexloom · 92 tokens

loom-communication

Use for communication between long-lived CodexLoom Agents: discovering domain owners, deciding when to contact another Agent, sending requests or notifications, replying to an agentmessage, checking queued delivery, and closing a request without a reply. Trigger whenever an Agent receives an agentmessage envelope or…

yan5xu/codexloom · 77 tokens

loom-external-messaging

Send and resolve governed external messages through CodexLoom. Use whenever an Agent receives an external Inbox message from Feishu/Lark, Slack, Parall, or another Connector; must reply, explicitly decline, or defer an external Inbox item; needs to publish proactively to an authorized Conversation Membership; sends…

yan5xu/codexloom · 104 tokens

domain-agent-coaching

Coach the design and ongoing reflection of long-lived domain Agents and Agent organizations. Use when defining or revising Identity, Domain, Scope, Organization or Collaboration relationships; deciding whether recurring work should become an Agent, Internal Agent, Skill, or Task; examining overlap, gaps, overloaded…

yan5xu/codexloom · 87 tokens

loom-topics

Coordinate bounded work that spans multiple Turns, days, or CodexLoom Agents through a shared Topic. Use when a workstream needs one Responsible Agent, scoped Participants, a versioned current brief, waiting conditions, evidence links, or recovery after time has passed; when receiving loomtopiccontext; or when…

yan5xu/codexloom · 107 tokens

loom-feishu

Read Feishu/Lark messages, topic replies, and chat history through CodexLoom's managed Connector. Use when a Feishu Inbox or dispatch lacks enough context; a chat, message, topic root, or reply chain must be inspected; current Feishu history is needed before replying; or the user asks what happened in a Feishu topic.…

yan5xu/codexloom · 92 tokens