deep-audit

deep-audit is a command for Claude Code from boparaiamrit/skills-by-amrit. It costs 43 tokens per session (1,241 once invoked), scanned B, original, MIT.

A five-part audit command that checks a buildable application’s build, pages, data movement, user journeys, and edge cases.

In plain words
What is it for?
Use it to verify builds, routes, data flow, user flows, and unusual inputs across an entire product or one selected audit pass.
Why use it?
It helps find problems that a quick review or earlier test may miss, then records them as actionable tasks.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the skills-by-amrit plugin — 33 skills, 34 commands, 9 agents shipped together

Good fit Use it to verify builds, routes, data flow, user flows, and unusual inputs across an entire product or one selected audit pass.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/boparaiamrit/skills-by-amrit/deep-audit
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/boparaiamrit/skills-by-amrit

Made for: Claude Code.

Or install skills-by-amrit, the plugin that ships this one along with the rest of its 33 skills, 34 commands, 9 agents.

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 deep-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/deep-audit/github.svg)](https://agentmods.dev/commands/boparaiamrit/skills-by-amrit/deep-audit)
Your own site
<a href="https://agentmods.dev/commands/boparaiamrit/skills-by-amrit/deep-audit"><img src="https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/deep-audit/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 deep-audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/boparaiamrit/skills-by-amrit/deep-audit"><img src="https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/deep-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,241 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00043 $0.01241
Opus 5 $0.00022 $0.00620
Sonnet 5 $0.00009 $0.00248
Haiku 4.5 $0.00004 $0.00124

Measured 12d ago against content hash d8acc69d4686, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

deep-audit scanned grade B 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 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf dist .next build __pycache__ 2>/dev/null

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

commands/deep-audit.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/deep-audit — Brutal Exhaustive Audit

Run a no-shortcuts, multi-pass audit of the entire product. Every file checked. Every route visited. Every flow tested. No exceptions.

Prerequisites

  • A buildable application
  • Time — this is thorough, not quick

Critical Rules

YOU CANNOT:
- Say "similar to above" — check each item independently
- Say "the rest are fine" — verify each one
- Skip a file because "it wasn't changed" — verify it anyway
- Trust previous verification — run it fresh
- Combine passes — each pass has a different focus
- Claim a pass is complete without a results table
- Estimate — measure and verify

Instructions

Step 1: Determine Scope

From $ARGUMENTS:

  • pass1 → Only Build & Static Analysis
  • pass2 → Only Route & Page Verification
  • pass3 → Only Data Flow Tracing
  • pass4 → Only User Flow Testing
  • pass5 → Only Edge Case Validation
  • all or empty → Run ALL 5 passes (recommended)

Step 2: Pass 1 — Build & Static Analysis

# Clean build
rm -rf dist .next build __pycache__ 2>/dev/null
npm run build 2>&1

# Type check
npx tsc --noEmit 2>&1

# Lint
npm run lint 2>&1

# Deps
npm audit --production 2>&1 | head -20

# Env vars
grep -rn "process\.env\.\|import\.meta\.env\." --include="*.ts" --include="*.tsx" --include="*.js" . | grep -vi "node_modules\|.git\|dist\|.next" | head -30

Record results table: Clean Build, Type Check, Lint, Dependencies, Environment. List EVERY error, not just counts.

Step 3: Pass 2 — Route & Page Verification

  1. Enumerate ALL routes (from router config or file-system routing)
  2. For EACH route, read the page component and verify:
    • Renders without errors
    • Content is real (not placeholder/hardcoded)
    • Responsive (mobile, tablet, desktop)
    • Navigation works

Record results table: Route, Loads, Content, Responsive, Navigation, Issues. EVERY route gets its own row. No "see above."

Step 4: Pass 3 — Data Flow Tracing

  1. Find all API calls and data sources
  2. For EACH one, trace: API → Service → Hook → Component → Output
  3. Verify: data is fetched, typed, transformed, error-handled
  4. Check: loading states, error states, empty states

Read the full file on GitHub · 164 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. 12d ago First seen · 164 lines · 43 tokens per session scan B d8acc69d4686

Subscribe to this mod's changes

deep-audit is a command published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,241 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.