A security-audit skill for applications made with rapid, AI-assisted coding. It finds vulnerabilities and missing protections, explains findings in Hebrew and English, and creates code that can be pasted into the app to address them.

Checking web, mobile, desktop, infrastructure, and continuous-integration projects for security issues and generating hardening fixes.

It provides a defined review process for identifying security problems while keeping repeatable checks separate from human judgment.

claudeguard — Skill for Claude Code by Freespirits

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Freespirits/claudeguard-il

Claude Code

/plugin install claudeguard-il

Made for: Claude Code.

Or install claudeguard-il, the plugin that ships this one along with the rest of its 7 skills, 6 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/freespirits/claudeguard-il/claudeguard.svg)](https://agentmods.dev/skills/freespirits/claudeguard-il/claudeguard)

Your own site

<a href="https://agentmods.dev/skills/freespirits/claudeguard-il/claudeguard"><img src="https://agentmods.dev/badge/skills/freespirits/claudeguard-il/claudeguard.svg" alt="Measured on agentmods" height="20"></a>

Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,987 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	$0.00152	$0.02987
Opus 5	$0.00076	$0.01494
Sonnet 5	$0.00030	$0.00597
Haiku 4.5	$0.00015	$0.00299

Measured 8d ago against content hash ffd954f476ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claudeguard 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 8d 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.

plugin/skills/claudeguard/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClaudeGuardIL

Security auditor and guard-builder for vibecoded apps. Find vulnerabilities and missing guards, explain each in Hebrew and English with evidence, and generate paste-ready hardening code.

Community project — NOT an official Anthropic product. Say this in every report header. פרויקט קהילתי — אינו מוצר רשמי של Anthropic.

The pipeline

Engine → Facts → Grader → Findings → Reviewers → Report.

The split matters and is not optional. A deterministic layer computes what can be computed and grades it; you review only what it could not decide. Re-grading its output yourself destroys the one thing v2 promises — that the same repo always produces the same severities.

Read references/methodology/README.md before your first scan. In Claude Code the engine and grader are real scripts; on claude.ai you apply the same method by hand from references/methodology/.

Workflow (follow in order)

Detect what the project is. Look for package.json (web/Node), next.config.*, AndroidManifest.xml / build.gradle (Android), Info.plist / *.xcodeproj (iOS), Electron main/webPreferences, Dockerfile / *.tf (IaC), .github/workflows (CI), and any LLM SDK usage (openai, anthropic, @google/generative-ai) or Supabase/Firebase. Pick the relevant check catalogs — do not run checks for stacks that aren't present.
Enumerate and grade (Tier 0, static — the default and always safe). In Claude Code: run node ${CLAUDE_PLUGIN_ROOT}/scripts/grader.mjs <path>. It runs the engine itself and returns findings, coverage and a verdict. Do not re-derive severity from it. On claude.ai: follow references/methodology/enumerate.md and grade.md against the pasted files, and declare your enumeration incomplete wherever it is.
Review what the rules could not decide. Work coverage.<set>.undeterminable — those are subjects that were enumerated but not settled, each with a reason. This is where the real value is: authorization that is present but wrong, workflow flaws, IDOR, prompt injection reaching a consequential tool. Findings you add carry provenance: reviewer and evidence.strength: judgement, which caps them at confidence likely. A reviewer's reading is never confirmed, no matter how sure it feels. Consult references/checks/ for what to look for per domain.

Read the full file on GitHub · 180 lines

Files

What ships with it

45 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

8d ago First seen · 180 lines · 152 tokens per session scan A ffd954f476ae

Subscribe to this mod's changes

claudeguard is a skill published in the GitHub repository Freespirits/claudeguard-il (2 stars, last pushed 1mo ago), licensed MIT. It adds 152 tokens to every session and 2,987 once invoked, about $0.0008 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens