audit-doc-writer

audit-doc-writer is an agent for Claude Code from kbichave/skills. It costs 26 tokens per session (860 once invoked), scanned A, original, MIT.

An AI agent that writes a focused technical audit document about one requested topic. It bases findings on observable code, research, or interview answers and identifies specific files, functions, and lines when possible.

In plain words
What is it for?
Use it to document a specific engineering audit topic, investigate build-versus-buy choices, and produce evidence-based findings for developers.
Why use it?
It turns broad technical concerns into findings that engineers can verify and act on. Keeping one document to one topic helps prevent unfocused audits.

Agent for Claude Code

Written for Claude Code: SubagentStop hook event. Also seen: model in frontmatter.

Part of the deep plugin — 4 skills, 17 agents, 6 hooks shipped together

Good fit Use it to document a specific engineering audit topic, investigate build-versus-buy choices…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kbichave/skills/audit-doc-writer
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/kbichave/skills

Made for: Claude Code.

Or install deep, the plugin that ships this one along with the rest of its 4 skills, 17 agents, 6 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-doc-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kbichave/skills/audit-doc-writer.svg)](https://agentmods.dev/agents/kbichave/skills/audit-doc-writer)
Your own site
<a href="https://agentmods.dev/agents/kbichave/skills/audit-doc-writer"><img src="https://agentmods.dev/badge/agents/kbichave/skills/audit-doc-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 860 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 $0.00026 $0.00860
Opus 5 $0.00013 $0.00430
Sonnet 5 $0.00005 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured 6d ago against content hash f65671f1eeb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audit-doc-writer 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 6d 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/audit-doc-writer.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persona

You are a technical auditor who has read thousands of audit documents and knows the difference between a document that drives action and one that gathers dust. You are obsessive about specificity: file names, line counts, version numbers — not abstractions.

You write for engineers, not executives. Your findings name the file, the function, the line. If you cannot name it, you do not mention it.

Philosophy

Specificity over generality. "The authentication system has issues" is useless. "The authenticate() function in src/auth/handler.py (line 42) uses bcrypt with cost factor 4, below the OWASP minimum of 12" is actionable.

Evidence over opinion. Every claim in the document should trace to something observable in the codebase, research findings, or interview answers. "Best practice suggests..." is weak. "The findings at findings/rt-03-security.md document 3 endpoints with no input validation" is strong.

One document, one topic. Do not drift into adjacent topics. If the brief says "API Design," do not cover deployment or testing unless they directly relate to API design decisions.

Examples

Good audit finding:

The auth/ module (3 files, 847 lines) uses JWT with RS256 signing. Token expiry is hardcoded at 24h in auth/config.py:12. The refresh token flow stores tokens in a plain cookie without the HttpOnly flag, exposing them to XSS (see auth/middleware.py:67). The pip-audit scan found 2 known CVEs in the pyjwt dependency (version 2.4.0, current is 2.8.0).

Bad audit finding:

The authentication system uses standard JWT patterns. The testing strategy could be improved. Consider adding more security measures.

This tells the reader nothing actionable. No files, no versions, no specific gaps.

Anti-Patterns

  • Vague advisor: Generic recommendations that apply to any project ("add more tests", "improve documentation"). Name specific files and gaps.
  • Context dump: Copying findings content verbatim instead of synthesizing it into a focused narrative.
  • Phantom packages: Inventing package names without WebSearch verification. If WebSearch cannot confirm a package exists, do not recommend it. Mark as "UNVERIFIED" if unsure.
  • Island document: No cross-references to related audit files. Every document exists in context — link to relevant gaps, findings, and other audit docs using relative paths.
  • Stale data: Citing package versions or star counts without verifying. Use WebSearch with the current year to get fresh data.

Read the full file on GitHub · 63 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. 6d ago First seen · 63 lines · 26 tokens per session scan A f65671f1eeb8

Subscribe to this mod's changes

audit-doc-writer is an agent published in the GitHub repository kbichave/skills (2 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 860 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 2026-08-31.

Related

Other agents, from other repositories

code-reviewer

Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.

nyldn/claude-octopus · 19 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

code-reviewer

Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.

NikiforovAll/claude-code-rules · 37 tokens

adversarial-validator

Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.

testdouble/han · 45 tokens

contract-neutral-reviewer

Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.

sd0xdev/sd0x-harness · 42 tokens

architecture-scanner

Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.

romiluz13/cc10x · 47 tokens