Code Auditor

A defensive security-review workflow for authorized analysis of software and systems. It emphasizes clear scope, preserved evidence, limited access, severity ratings, and practical fixes.

In plain words
What is it for?
Use it to audit code, document vulnerabilities, assess their severity, recommend remediation, and verify that fixes address the reported risks.
Why use it?
It helps identify and communicate security risks without drifting into unauthorized access, credential theft, stealth, or evasion.

Skill for Claude CodeCodex

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 skills/ahmadrrrtx/xr/code_auditor
Any agent
npx skills add ahmadrrrtx/xr --skill code_auditor
Clone the repo
git clone --depth 1 https://github.com/ahmadrrrtx/xr

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 315 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 $0.00022 $0.00315
Opus 5 $0.00011 $0.00158
Sonnet 5 $0.00004 $0.00063
Haiku 4.5 $0.00002 $0.00032

Measured 2d ago against content hash a6184e8dd0bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Code 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 2d 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.

Origin

Copies of this mod

6 near-identical copies found in the catalogue:

skills/code_auditor/SKILL.md · 40 lines

What it actually says

Code Auditor

Professional Identity

You are XR's Code Auditor Skill. You should feel like hiring a careful professional, not installing a prompt.

Mission

Code Auditor delivers defensive, authorized, auditable security analysis with explicit scope boundaries and risk handling.

Operating Rules

  • Operate only in authorized defensive scope.
  • Do not provide stealth, persistence, credential theft, or evasion instructions.
  • Prioritize containment, evidence preservation, and least privilege.
  • Report severity with evidence and remediation.

Default Workflow

  1. Clarify the objective, user constraints, available inputs, and success criteria.
  2. Create a compact plan with risks and required approvals.
  3. Execute with domain best practices and clear artifacts.
  4. Validate the output against the criteria, safety constraints, and edge cases.
  5. Handoff with decisions, residual risks, and next steps.

Output Standard

  • Use structured headings.
  • Be specific and actionable.
  • Call out assumptions.
  • Include verification steps.
  • If files, shell, network, memory, voice, providers, MCP, plugins, or computer-control actions are needed, respect XR approvals and permissions.
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. 2d ago First seen · 40 lines · 22 tokens per session scan A a6184e8dd0bf

Subscribe to this mod's changes

Code Auditor is a skill published in the GitHub repository ahmadrrrtx/xr (5 stars, last pushed 7d ago), licensed MIT. It adds 22 tokens to every session and 315 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 skills, from other repositories

html-ppt-zhangzara-monochrome

A grant proposal on CRISPR base-editing for sickle-cell disease — the hypothesis, the approach, the milestones, and the risk. Built as a decision-grade academic research deck for grant review committee.

nexu-io/open-design · 54 tokens

deck-hermes-cyber

黑底 + CRT 网格扫描线 + $ 命令行标题 + 薄荷绿大字 + 三档 tag.

nexu-io/html-anything · 34 tokens

code-review

Systematic code review for bugs, security, style, and performance.

vstorm-co/pydantic-deepagents · 16 tokens

red-team-tribunal

Multi-agent adversarial verification system. Use when you need thorough code review, security auditing, or quality validation. Spawns three specialized agents (Skeptic, User Proxy, Optimizer) that must reach consensus before code can be approved.

aegntic/cldcde · 54 tokens

brainllm

Persistent memory and knowledge graph via the BrainLLM (Trilium) MCP. Activate at the start of every session without exception — governs orientation, remembering, recall, completion, lifecycle, maintenance, and interconnection. Trigger immediately on any first user message. Also trigger whenever: memory is referenced…

miisodev/BrainLLM · 115 tokens

cuj-guardian

Run and triage AI Atelie's Critical User Journey (CUJ) for every PR — the single end-to-end test that proves a user can open the app, create a project, drive the Claude Code agent, and see the canvas render. Before running, gate by inspecting the PR diff for changes that plausibly affect the journey (routes…

aiatelie/ai-atelie · 137 tokens