audit-reviewer

audit-reviewer is an agent for Claude Code from AleksandarBisevac/claude-plugins. It costs 68 tokens per session (461 once invoked), scanned A, original, MIT.

A read-only reviewer that signs off one phase of an audit by examining the code changes in that phase. It reports findings but cannot edit files.

In plain words
What is it for?
Use it to check a phase diff for missed bugs, security regressions, incorrect outcomes, leftover debug code, and violations of the project's review checklist.
Why use it?
It gives a focused review of the requested change and separates finding problems from making the fixes.

Agent for Claude Code

Written for Claude Code: effort in frontmatter.

Part of the audit plugin — 2 skills, 20 commands, 4 agents, 4 hooks shipped together

Good fit Use it to check a phase diff for missed bugs, security regressions, incorrect outcomes, leftover debug code, and violations of the project's review checklist.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/aleksandarbisevac/claude-plugins/audit-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/AleksandarBisevac/claude-plugins

Made for: Claude Code.

Or install audit, the plugin that ships this one along with the rest of its 2 skills, 20 commands, 4 agents, 4 hooks.

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 audit-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/aleksandarbisevac/claude-plugins/audit-reviewer/github.svg)](https://agentmods.dev/agents/aleksandarbisevac/claude-plugins/audit-reviewer)
Your own site
<a href="https://agentmods.dev/agents/aleksandarbisevac/claude-plugins/audit-reviewer"><img src="https://agentmods.dev/badge/agents/aleksandarbisevac/claude-plugins/audit-reviewer/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 audit-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/aleksandarbisevac/claude-plugins/audit-reviewer"><img src="https://agentmods.dev/badge/agents/aleksandarbisevac/claude-plugins/audit-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 461 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 $0.00068 $0.00461
Opus 5 $0.00034 $0.00230
Sonnet 5 $0.00014 $0.00092
Haiku 4.5 $0.00007 $0.00046

Measured 10d ago against content hash 04c64ccab607, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

audit-reviewer 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 10d 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.

plugins/audit/agents/audit-reviewer.md · 35 lines

What it actually says

You review ONE phase's changes at sign-off. The orchestrator's prompt gives you the phase's diff scope (git diff <baseRef> -- <files>), the phase's desired outcome, and — when the project configures one — a review skill name.

Hard rules:

  • If a review skill name was given: invoke it FIRST via the Skill tool and apply its checklist to the diff. Otherwise review for: correctness bugs the tests would miss, violations of the phase's desired outcome, security regressions, and dead/leftover debug code.
  • You may run read-only git commands (git diff, git log, git show) and the test/lint commands you were given — nothing that mutates the tree, history, or state. You have no edit tools by design: report, don't fix.
  • Charge findings to the DIFF, not the codebase: pre-existing problems outside the changed lines go into preExisting, not findings.
  • Treat evidence-free verification claims as unverified work: a "verified/tested/checked" that names no exact command and exit code (or concrete observation) may be rejected on that basis alone.
  • Be precise and small: each finding names file:line, the issue, and a concrete resolution. No style nitpicks unless the review skill demands them.

Return format — your ENTIRE final message is ONLY this JSON object (no prose):

{"findings": [{"id": 1, "severity": "low|med|high", "file": "path:lines", "issue": "...", "resolution": "..."}, ...], "preExisting": [ ...same shape... ], "verdict": "clean | findings"}

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. 10d ago First seen · 35 lines · 68 tokens per session scan A 04c64ccab607

Subscribe to this mod's changes

audit-reviewer is an agent published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 461 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.

Related

Other agents, from other repositories

simplification-reviewer

Measures whether the same functionality can be delivered with less - reuse that was missed, indirection that forwards without deciding, generality nothing consumes, control flow with a flatter equivalent, and response payloads that spend more of the calling agent's context than their information is worth.

OutSystems/outsystems-mcp · 59 tokens

consistency-reviewer

Verifies that this repo's agent-facing surface - skill-doc instructions, slash-command frontmatter, and plugin manifests - accurately reflects actual behavior and stays in lockstep across the five parallel skill docs and four manifest files.

OutSystems/outsystems-mcp · 48 tokens

docs-reviewer

Ensures documentation completeness and manifest correctness for changes that affect user-facing or structural aspects of the repository.

OutSystems/outsystems-mcp · 24 tokens

error-handling-reviewer

Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.

OutSystems/outsystems-mcp · 24 tokens

cook-audit

You are the audit station of the jeff brigade, working one order in a fresh context. You run when plan flagged a security-relevant surface (auth, input handling, secrets, deserialization, file/network/process access, crypto, dependencies, anything privilege- or data-exposing), or when the mechanical scan floor forced…

johanthoren/jeff · 0 tokens

cook-review

You are the review station of the jeff brigade, working one order in a fresh context. You did not write this code or its tests: your independence is the point. You are the defense against momentum and self-approval bias.

johanthoren/jeff · 56 tokens