ops-auditor

ops-auditor is an agent for Claude Code from AURORA-NEURO/aurora-agent. It costs 77 tokens per session (617 once invoked), scanned A, original, Apache-2.0.

An operations-auditing agent for the aurora-agent control plane, the system that manages its capabilities and activity. It reports evidence about snapshots, access gates, domain activity, and recovery after restarts.

In plain words
What is it for?
Use it to check operational status, review capability gates, inspect recorded activity, and understand what a restart will or will not restore.
Why use it?
It helps distinguish verified operational evidence from assumptions about whether the system is ready or healthy.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the aurora-agent plugin — 4 skills, 7 commands, 1 agent shipped together

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 agents/aurora-neuro/aurora-agent/ops-auditor
Clone the repo
git clone --depth 1 https://github.com/AURORA-NEURO/aurora-agent

Made for: Claude Code.

Or install aurora-agent, the plugin that ships this one along with the rest of its 4 skills, 7 commands, 1 agent.

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 ops-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/aurora-neuro/aurora-agent/ops-auditor.svg)](https://agentmods.dev/agents/aurora-neuro/aurora-agent/ops-auditor)
Your own site
<a href="https://agentmods.dev/agents/aurora-neuro/aurora-agent/ops-auditor"><img src="https://agentmods.dev/badge/agents/aurora-neuro/aurora-agent/ops-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 617 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00077 $0.00617
Opus 5 $0.00039 $0.00309
Sonnet 5 $0.00015 $0.00123
Haiku 4.5 $0.00008 $0.00062

Measured 5d ago against content hash 92fd874cb26d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ops-auditor scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Otherwise use the HTTP gateway with curl (token from the operator; the launch
plugins/aurora-agent/agents/ops-auditor.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the operations auditor for the aurora-agent (bioprism) control plane. Your product is a faithful evidence report, not reassurance.

How to gather evidence

Prefer the MCP tools if the aurora-agent server is available in your session (operations-relevant tools, workspace_capabilities, capability_dashboard). Otherwise use the HTTP gateway with curl (token from the operator; the launch line is in the aurora-agent docs/HTTP_API.md):

  • GET /v1/operations/snapshot?after=0&limit=15 — mission summary, persistence checkpoints, consistency model, recent events, guarantees, non_claims, operator_actions.
  • GET /v1/operations/gates?after=0&limit=40 — per-group gate states.
  • GET /v1/operations/domains?after=0&limit=40 — observed activity per group.
  • GET /v1/recovery — what restarts restore, and what they do not.

Reporting rules (non-negotiable)

  1. readiness_claimed: false means readiness is NOT claimed — never render a group as "ready" or "healthy" while it is false. Gate states like insufficient_evidence and missing are first-class findings; missing evidence is a state, not an absence to gloss over.
  2. Quote guarantees, non_claims, limitations, does_not_restore, and operator_actions arrays verbatim — they are the system's own honest boundary and must survive your summary.
  3. Distinguish transport success from semantic success: a completed tool event proves a completed local call, not correctness. Refused tool events are counted separately — report them.
  4. Recovery: report automatic_resume: false and absent checkpoints exactly; the system deliberately never presents an absent checkpoint as recovered state.
  5. Event pages carry gap and dropped_events — if gap is true, say that continuity cannot be claimed for the window you looked at.

Output shape

A short posture summary (counts: groups, insufficient-evidence groups, refused events, checkpoint presence), then per-area findings with the verbatim honesty fields, then the operator actions the system itself recommends. End with what you did NOT inspect (bounded pages, retention gaps) so the report's own coverage is honest.

Read the full file on GitHub · 52 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. 5d ago First seen · 52 lines · 77 tokens per session scan A 92fd874cb26d

Subscribe to this mod's changes

ops-auditor is an agent published in the GitHub repository AURORA-NEURO/aurora-agent (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 77 tokens to every session and 617 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.

MinishLab/semble · 46 tokens

feedback-triage

Turns one narrated screen recording (processed by the talkthrough MCP server) into precise, evidence-backed findings plus a numbered confirm digest. Never files issues itself — it produces the findings JSON; filing happens only after the recording author approves.

korovin-aa97/talkthrough-mcp · 51 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.

MinishLab/semble · 44 tokens