audit

Comprehensive codebase audit with scoring and prioritized refactoring plan.

Command for Claude Code

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 commands/jnarowski/agentcmd/audit
Clone the repo
git clone --depth 1 https://github.com/jnarowski/agentcmd

Made for: Claude Code.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,230 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00012 $0.03230
Opus 5 $0.00006 $0.01615
Sonnet 5 $0.00002 $0.00646
Haiku 4.5 $0.00001 $0.00323

Measured today against content hash 5198fdb08e38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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 today.

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.

.claude/commands/audit.md · 486 lines

How it starts

The opening of the file, as written. The whole thing — 486 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Codebase

Perform comprehensive codebase audit focused on developer experience and code quality. Analyzes architecture, clarity, types, duplication, errors, standards, structure, debt, dependencies, and tests. Optimized for small projects (not enterprise).

Variables

  • $mode: $1 (optional, default: cleanup) - Analysis depth: cleanup (critical+moderate only), standard (all severities), deep (comprehensive with parallel agents)
  • $scope: $2 (optional, default: full) - Audit scope: full, frontend, backend, workflow, types, tests

Instructions

  • Focus on small project best practices - pragmatic over enterprise patterns
  • Goal: improve developer experience and code maintainability
  • Generate actionable recommendations with clear solutions
  • Score each section with points-based system (X/100 total)
  • Prioritize refactoring by impact (high/medium/low)
  • Be concise - sacrifice grammar for brevity in findings
  • Report file paths with line numbers for all issues found

Workflow

  1. Validate arguments

    • Set mode = "cleanup" if not provided
    • Set scope = "full" if not provided
    • Validate mode is one of: cleanup, standard, deep
    • Validate scope is one of: full, frontend, backend, workflow, types, tests
  2. Deploy audit agents based on mode

    • cleanup mode: Deploy 3-5 targeted agents focusing on critical+moderate issues only
    • standard mode: Deploy 6-8 agents covering all severity levels
    • deep mode: Deploy all 10 parallel agents with ultrathink depth
  3. Filter agents by scope

    • If scope = "frontend": only deploy agents 2, 3, 4, 7, 10
    • If scope = "backend": only deploy agents 1, 3, 4, 5, 7, 10
    • If scope = "workflow": focus agents on specified domain in apps/app/src/client/pages/projects/workflows and server/domain/workflow
    • If scope = "types": only deploy agent 3
    • If scope = "tests": only deploy agent 10
    • If scope = "full": deploy all relevant agents
  4. Synthesize results

    • Aggregate findings from all agents
    • Calculate total score (sum of section scores)
    • Categorize issues by severity: critical, moderate, minor
    • Generate prioritized refactoring plan

Read the full file on GitHub · 486 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. today First seen · 486 lines · 12 tokens per session scan A 5198fdb08e38

Subscribe to this mod's changes

audit is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 12 tokens to every session and 3,230 once invoked, about $0.0001 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 2026-09-01.