A read-only project risk check used before starting AI Project Guard. It reviews the project structure, tools, tests, governance files, and files that may affect authentication, scheduled jobs, database changes, or data access.

Use it to inspect a project before running AI Project Guard initialization. It can highlight the package and build tools, frameworks, test and migration systems, existing instruction files, and potentially dangerous modules.

It helps identify risky code and missing project rules before an automated governance setup changes how an agent works with the codebase.

scan-guard — Skill for Claude Code by zhangguangzhi001-bot

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.

Any agent

npx skills add zhangguangzhi001-bot/ai-project-guard --skill scan-guard

Clone the repo

git clone --depth 1 https://github.com/zhangguangzhi001-bot/ai-project-guard

Made for: Claude Code.

Or install ai-project-guard, the plugin that ships this one along with the rest of its 3 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zhangguangzhi001-bot/ai-project-guard/scan-guard/github.svg)](https://agentmods.dev/skills/zhangguangzhi001-bot/ai-project-guard/scan-guard)

Your own site

<a href="https://agentmods.dev/skills/zhangguangzhi001-bot/ai-project-guard/scan-guard"><img src="https://agentmods.dev/badge/skills/zhangguangzhi001-bot/ai-project-guard/scan-guard/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zhangguangzhi001-bot/ai-project-guard/scan-guard"><img src="https://agentmods.dev/badge/skills/zhangguangzhi001-bot/ai-project-guard/scan-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 771 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.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.00771
Opus 5	$0.00028	$0.00385
Sonnet 5	$0.00011	$0.00154
Haiku 4.5	$0.00006	$0.00077

Measured 12d ago against content hash 64d99c882afa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

scan-guard 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 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.

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/scan-guard/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scan Guard

Perform a read-only governance risk scan before initialization.

This skill is a Claude Code workflow guide. As the CLI matures, prefer the CLI's scan command when available. Until then, this skill helps Claude Code gather advisory information safely.

When to Use

User wants a risk overview before running ai-project-guard init.
User asks for "扫描项目风险", "audit project", "check governance", "scan guard".
User runs /scan-guard.

Core Pattern

Step 1: Quick structural scan

Walk the project root and report:

Package manager / build tool detected
Framework indicators (Spring, Vue, React, Django, Express, etc.)
Test framework indicators
Database migration tool indicators
Existing governance files (CLAUDE.md, .claude/, .cursor/rules/, etc.)

Step 2: Dangerous module candidates

Flag files and patterns that typically represent high risk:

Pattern	Risk
`Security.java`, `Auth.ts`, `auth/*`	Authentication bypass risk
`Scheduler`, `Cron`, `Job`	Production job disruption
`db/migration/`, `migration*.sql`	Schema breakage risk
`mapper/.xml`, `Repository*.java`	Data access contract risk
`Controller`, `Router`, `routes`	API contract breakage
`application.yml`, `.env`	Configuration risk
Stripe/PayPal/third-party API clients	External integration risk

Step 3: Legacy module candidates

Flag files and patterns suggesting legacy/compatibility code:

deprecated, legacy, old, v1, compat, adapter
Comments containing "don't delete", "keep for compatibility", "历史原因"

Step 4: Contract candidates

Identify likely contracts:

ApiResponse<T>, response envelope classes
Status enums and string constants
TypeScript API type files
Database migration files
Shared DTO/VO/Entity classes

Step 5: Missing governance assessment

Check whether governance files exist and report gaps:

CLAUDE.md              [EXISTS / MISSING]
CLAUDE.architecture.md [EXISTS / MISSING]
CLAUDE.lessons.md      [EXISTS / MISSING]
CLAUDE.local.md        [EXISTS / MISSING]
.claude/agents/        [EXISTS / MISSING]
.claude/commands/      [EXISTS / MISSING]
.claude/workflows/     [EXISTS / MISSING]

Read the full file on GitHub · 96 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.

12d ago First seen · 96 lines · 57 tokens per session scan A 64d99c882afa

Subscribe to this mod's changes

scan-guard is a skill published in the GitHub repository zhangguangzhi001-bot/ai-project-guard (5 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 771 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.

Security

systematic-debugging

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

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens