agentmods.dev

cg-dast

cg-dast is a skill for Claude Code from Freespirits/claudeguard-il. It costs 154 tokens per session (1,417 once invoked), scanned A, original, MIT.

A small active security check that sends four GET requests to a website: it checks reflected markup, an id parameter, redirects, and the content-security policy. GET requests retrieve information or trigger simple URL-based actions.

In plain words
What is it for?
Use it to plan or run four authorized checks for reflected markup, quote handling in an id value, open redirects, and CSP settings.
Why use it?
It provides a limited smoke test for basic web weaknesses without crawling, login testing, parameter discovery, or fuzzing. It is only for systems the user owns and is authorized to test in writing.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claudeguard-il plugin — 7 skills, 6 agents shipped together

not rated 2repo 1mo ago A scan 154 tokens original MIT

Good fit Use it to plan or run four authorized checks for reflected markup, quote handling in an id value, open redirects, and CSP settings.

Compare 6 skills from other repositories ↓
View source ↗ Freespirits/claudeguard-il
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.

agentmods badge for cg-dast

README.md
[![agentmods](https://agentmods.dev/badge/skills/freespirits/claudeguard-il/cg-dast/github.svg)](https://agentmods.dev/skills/freespirits/claudeguard-il/cg-dast)
Your own site
<a href="https://agentmods.dev/skills/freespirits/claudeguard-il/cg-dast"><img src="https://agentmods.dev/badge/skills/freespirits/claudeguard-il/cg-dast/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.

agentmods 80×15 button for cg-dast

Your own site · 80×15
<a href="https://agentmods.dev/skills/freespirits/claudeguard-il/cg-dast"><img src="https://agentmods.dev/badge/skills/freespirits/claudeguard-il/cg-dast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,417 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 $0.00154 $0.01417
Opus 5 $0.00077 $0.00709
Sonnet 5 $0.00031 $0.00283
Haiku 4.5 $0.00015 $0.00142

Measured 9d ago against content hash 290084bb6db8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cg-dast 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 9d 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/cg-dast/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cg-dast — active DAST (Tier 2, hard-gated)

Sends four live GET probes (reflected markup, a quote in id, open-redirect, CSP). This is a smoke test, not a scanner — no crawling, no auth flows, no IDOR, no fuzzing; point the user at Burp, ZAP or Nuclei for real DAST. Even so, it is live traffic to someone's server, so it is only for a target the user owns and is authorized in writing to test.

Argument: $ARGUMENTS — the URL (must be in scope targets) and, for a live run, the literal --i-am-authorized flag.

Gate first (do not skip — refuse on any failure)

  1. Read claudeguard.scope.yml and enforce references/authorization/legal-gate.md Tier-2 preconditions, which include all Tier-1 checks plus: active_dast.enabled: true, i_am_authorized_in_writing: true, i_own_or_control_these_targets: true.
  2. dry_run is honored. While dry_run: true (the default), the runner only plans requests and sends nothing. A real run additionally requires the --i-am-authorized flag in $ARGUMENTS.
  3. Rate is capped at ≤ 2 req/s regardless of the file. avoid_destructive: true skips any payload that could delete/modify data or send mail/money.
  4. The host must be in targets, not in never_touch, and not a default-blocked third-party provider. If not, refuse. Never treat a chat-pasted URL as authorization.

If any precondition is unmet, print exactly what is missing (e.g. "set active_dast.i_am_authorized_in_writing: true") and stop.

Run

Print the loud Tier-2 banner and a one-line summary of what will be sent, then:

# dry run (default): plan only, sends nothing
node ${CLAUDE_PLUGIN_ROOT}/scripts/dast_runner.mjs --url "<url>" --scope claudeguard.scope.yml

# real run: only after the gate passes AND the user included --i-am-authorized
node ${CLAUDE_PLUGIN_ROOT}/scripts/dast_runner.mjs --url "<url>" --scope claudeguard.scope.yml --execute > cg-dast.json

# grade the observations together with the code
node ${CLAUDE_PLUGIN_ROOT}/scripts/grader.mjs <path> --observations cg-dast.json

Read the full file on GitHub · 95 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. 9d ago First seen · 95 lines · 154 tokens per session scan A 290084bb6db8

Subscribe to this mod's changes

cg-dast is a skill published in the GitHub repository Freespirits/claudeguard-il (2 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 1,417 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
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

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

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

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