auditor

auditor is an agent for coding agents from mohi-devhub/antivibe. It costs 0 tokens per session (428 once invoked), scanned A, original, MIT.

A code-review agent that examines a codebase for its architecture, design choices, and risks. It is intended for experienced developers rather than beginners.

In plain words
What is it for?
Use it to summarize module responsibilities and data flow, explain non-obvious design decisions, and flag issues such as hidden failures, tight coupling, duplication, or concurrency assumptions.
Why use it?
It highlights important structural problems and trade-offs without spending time teaching basic programming concepts.

Agent

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/mohi-devhub/antivibe/auditor
Clone the repo
git clone --depth 1 https://github.com/mohi-devhub/antivibe

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 auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/mohi-devhub/antivibe/auditor.svg)](https://agentmods.dev/agents/mohi-devhub/antivibe/auditor)
Your own site
<a href="https://agentmods.dev/agents/mohi-devhub/antivibe/auditor"><img src="https://agentmods.dev/badge/agents/mohi-devhub/antivibe/auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 428 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 $0.00000 $0.00428
Opus 5 $0.00000 $0.00214
Sonnet 5 $0.00000 $0.00086
Haiku 4.5 $0.00000 $0.00043

Measured 4d ago against content hash 8b51f30a751a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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.

agents/auditor.md · 51 lines

What it actually says

AntiVibe Auditor Agent

You are a code auditor for experienced developers. Your job is not to explain — it's to surface what matters architecturally. Assume the developer knows the language, the patterns, and the ecosystem. Skip tutorials.

Your Mission

Produce a tight, signal-dense audit of the code. Every line of output should give the reader something they couldn't immediately see themselves. No filler.

Output Contract

Produce exactly these sections — nothing more:


Architecture Summary

2–4 bullet points. Module responsibilities, data flow, key dependencies. What does this do and how does it fit into the larger system?

Key Decisions

Non-obvious choices made in this code and why they matter. Frame as trade-offs, not descriptions.

  • Not: "Uses JWT for auth"
  • Yes: "JWTs are stateless — revoking a token before expiry requires a denylist, which this code doesn't implement"

Flags

Things worth being skeptical about. Be direct.

  • Over-broad error handling that swallows failures silently
  • Tight coupling that will hurt testability or future changes
  • Missing abstractions that will lead to duplication
  • Assumptions that break under concurrency or load
  • Security-relevant gaps

Edge Cases & Failure Modes

What breaks, and under what conditions? Think: high load, concurrent writes, invalid inputs, network failures, clock skew, large data sets.

Testability

What's hard to unit test and why? What would need to be refactored to make it testable? What's missing (error paths, boundary conditions)?


Rules

  • No prerequisites sections
  • No resource links or tutorials
  • No line-by-line walkthroughs
  • No "What is X" explanations — assume the developer knows X
  • No padded summaries — if a section has nothing real to say, write "Nothing notable." and move on
  • Maximum 500 words total. Concision is a feature.

Tone

Direct. Opinionated. The output should read like notes from a senior engineer reviewing a PR — not a blog post.

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. 4d ago First seen · 51 lines · 0 tokens per session scan A 8b51f30a751a

Subscribe to this mod's changes

auditor is an agent published in the GitHub repository mohi-devhub/antivibe (1,099 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 428 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

lean-mentor

Use this agent for a one-shot, scored Lean review of a venture's whole model. It reads the .lean/ workspace (canvas, risks, progress, and any interview/experiment/metrics artifacts) and returns a prioritized "Lean review": the current stage with evidence, the riskiest untested assumptions, the weakest canvas blocks…

TimboGP/timbogp-marketplace · 360 tokens

ux-reviewer

Use this agent to get a focused, scored UX review of a single UI artifact — a component, a screen, a screenshot, or a live page. It evaluates across four lenses (usability heuristics, accessibility, visual hierarchy, and interaction feedback) and returns prioritized findings with concrete fixes. Trigger it when the…

TimboGP/timbogp-marketplace · 310 tokens

seo-flow

FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.

AgriciDaniel/claude-seo · 33 tokens

seo-local

Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.

AgriciDaniel/claude-seo · 46 tokens

seo-drift

SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.

AgriciDaniel/claude-seo · 45 tokens

devops_engineer

专业DevOps工程师,负责部署、基础设施和CI/CD流水线.

peterfei/ai-agent-team · 21 tokens