cg-harden

cg-harden is a skill for Claude Code from Freespirits/claudeguard-il. It costs 65 tokens per session (1,136 once invoked), scanned A, original, MIT.

A command that writes code examples for fixing ClaudeGuardIL security findings without changing project files.

In plain words
What is it for?
Use it to generate fixes for specific findings, security areas, or all findings from the latest grader run, including validation, headers, middleware, and database policies.
Why use it?
It turns reported problems into paste-ready safeguards while leaving the developer in control of applying them.

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

Good fit Use it to generate fixes for specific findings, security areas, or all findings from the latest grader run, including validation, headers, middleware, and database policies.

Compare 6 skills from other repositories ↓
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-harden

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/freespirits/claudeguard-il/cg-harden"><img src="https://agentmods.dev/badge/skills/freespirits/claudeguard-il/cg-harden.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,136 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 $0.00065 $0.01136
Opus 5 $0.00032 $0.00568
Sonnet 5 $0.00013 $0.00227
Haiku 4.5 $0.00006 $0.00114

Measured 10d ago against content hash bf9aadaa7018, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cg-harden 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 10d 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-harden/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cg-harden — generate guards (no file changes)

Produce the concrete fix for one or more findings, tailored to the user's actual code. This does not edit anything — it outputs code to paste. To apply automatically, use /cg-fix.

Argument: $ARGUMENTS — a finding id (CG-DB-001), a domain (web), or all (default: the findings and coverage from the most recent grader run).

Your input is the graded output

grader.mjs returns findings and coverage. Both are guard targets, for different reasons.

Per finding, the fields you need:

  • guardguard-recipes/<name>.md#<anchor>, resolved against ${CLAUDE_PLUGIN_ROOT}/skills/claudeguard/references/. That anchor is the recipe. Open it.
  • evidencean object: { strength, nameOnly, why, at: [...] }. evidence.at[] holds { file, line, snippet } — where the guard goes. evidence.why is the mechanism, and it belongs in your summary. (In v1 evidence was the bare array that is now evidence.at.)
  • severity, confidence, provenance, assumption — for ordering and for telling the user how much to trust the finding you are about to have them act on. Do not recompute them; the grader is the only authority on severity and confidence.

Unlike /cg-fix, you are not restricted to confirmed findings — you write code, you do not apply it, and a human reads the diff before it lands. But say plainly which is which: a likely finding from a reviewer and a confirmed one from a rule warrant different urgency, and the assumption field is what the user checks before pasting.

Coverage rows are guard targets too

coverage.<set>.undeterminable rows are not findings — no rule could establish anything about them — and that is exactly what makes them good places to harden. A route whose auth could not be verified is the ideal spot for an explicit, checked guard: adding one converts "we could not tell" into "it is enforced here, in one readable line". Same for a SECURITY DEFINER function whose auth check could not be shown to gate the body, and for an LLM call site whose limits could not be confirmed.

Read the full file on GitHub · 79 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. 10d ago First seen · 79 lines · 65 tokens per session scan A bf9aadaa7018

Subscribe to this mod's changes

cg-harden is a skill published in the GitHub repository Freespirits/claudeguard-il (2 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,136 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

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