security-audit

security-audit is a skill for Claude Code, Codex from HalidSaglam/saglitzsecure. It costs 60 tokens per session (1,939 once invoked), scanned A, original, MIT.

A security-audit procedure for examining an existing website, backend API, iOS or macOS app, or GitHub repository. It defines how to scan the project, interpret evidence, and report which areas were or were not covered.

In plain words
What is it for?
Use it when asking whether existing code or a repository is safe, including web, backend, and Apple-platform projects.
Why use it?
It makes security reviews repeatable and keeps the report clear about evidence and coverage instead of presenting an incomplete scan as a clean result.

Skill for Claude CodeCodex

Part of the saglitzsecure plugin — 4 skills, 1 MCP server shipped together

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/halidsaglam/saglitzsecure/security-audit
Any agent
npx skills add HalidSaglam/saglitzsecure --skill security-audit
Clone the repo
git clone --depth 1 https://github.com/HalidSaglam/saglitzsecure

Made for: Claude Code, Codex.

Or install saglitzsecure, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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 security-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/halidsaglam/saglitzsecure/security-audit.svg)](https://agentmods.dev/skills/halidsaglam/saglitzsecure/security-audit)
Your own site
<a href="https://agentmods.dev/skills/halidsaglam/saglitzsecure/security-audit"><img src="https://agentmods.dev/badge/skills/halidsaglam/saglitzsecure/security-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,939 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 $0.00060 $0.01939
Opus 5 $0.00030 $0.00970
Sonnet 5 $0.00012 $0.00388
Haiku 4.5 $0.00006 $0.00194

Measured 2d ago against content hash 3e582029b099, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-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 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.

skills/security-audit/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security audit

An audit is a method, not a menu: which tool is called in which order, which output is never spoken about before it is read, what counts as evidence and how the result is presented are all settled. Do not skip the order below; step 2 in particular comes before step 3.

If the question arrived before the code was written — "how do I build this safely?" — this skill is not the one in play; that question belongs to the secure-by-default skill. This skill audits what has already been written.

1. Scan

Call scan_project.

  • path: the absolute path of the directory to scan. If the user gave no path, use the root of the project you are working in, and say in your answer which directory you scanned.
  • target: "auto" unless the user says otherwise. Passing "web" or "apple" by hand does not run the rules belonging to the other target — it narrows coverage. Tell the user about every choice that narrows coverage.
  • minSeverity: do not pass one by default. A threshold hides low-severity findings and makes the report look "clean"; set one only if the user asks for it, and say so in the report.

The scan makes no network requests and runs no code. Findings come only from the files in the repository.

2. Read the coverage statement before you tell the user anything

Before you pass on a single sentence of the report, read all three parts of the coverage field:

  • coverage.rulesNotRun — the rules that did not run in this pass. If a rule did not run, that area was not audited; it is not clean. If the reason is a missing capability (for example apple/ats-arbitrary-loads in a repository that has no Apple configuration) this is expected, and it is reported as such. If the reason is that the rule threw, that is a tool failure and it is reported to the user as a failure — never swallowed in silence.
  • coverage.skipped — files that were never read, and why they were not read. If a file was not read, say nothing about anything inside it.
  • coverage.notes — the limits that hold on every run. It carries at least these: no network request is made (response headers added by a CDN or a reverse proxy cannot be seen, so findings such as header/csp-missing reflect only the configuration in the repository); configuration files are read as text, not executed; no data-flow (taint) analysis is performed; test and fixture files are scanned too, so a deliberately insecure example cannot be told apart from a real vulnerability.

Read the full file on GitHub · 135 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. 2d ago First seen · 135 lines · 60 tokens per session scan A 3e582029b099

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository HalidSaglam/saglitzsecure (0 stars, last pushed 5d ago), licensed MIT. It adds 60 tokens to every session and 1,939 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens