mtk-agent-toolkit: Skill for Claude Code

.claude/skills/security-and-hardening/SKILL.md

security-and-hardening is a skill for Claude Code from moberghr/mtk-agent-toolkit. It costs 37 tokens per session (864 once invoked), scanned A, original, MIT.

A set of development guidelines for securing software changes involving login access, secrets, audited records, infrastructure, or outside data.

In plain words
What is it for?
Use it to review trust boundaries, permissions, sensitive data, logging, input validation, and infrastructure changes.
Why use it?
It helps catch security, privacy, authorization, and audit-trail problems while the change is being designed.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md; mentions Codex.

This is moberghr/mtk-agent-toolkit's own configuration. It tells Claude Code how to work on mtk-agent-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mtk-agent-toolkit configures →

Part of the mtk plugin — 45 skills, 6 agents, 7 hooks, 1 MCP server shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/moberghr/mtk-agent-toolkit/main/.claude/skills/security-and-hardening/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/moberghr/mtk-agent-toolkit

Made for: Claude Code.

Or install mtk, the plugin that ships this one along with the rest of its 45 skills, 6 agents, 7 hooks, 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-and-hardening

README.md
[![agentmods](https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/security-and-hardening/github.svg)](https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/security-and-hardening)
Your own site
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/security-and-hardening"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/security-and-hardening/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 security-and-hardening

Your own site · 80×15
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/security-and-hardening"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/security-and-hardening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 864 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Agent Snooping · line 23
    Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
    Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
  • medium Agent Snooping · line 68
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00037 $0.00864
Opus 5 $0.00018 $0.00432
Sonnet 5 $0.00007 $0.00173
Haiku 4.5 $0.00004 $0.00086

Measured yesterday against content hash e1482f123c23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

security-and-hardening scanned grade A with 1 finding 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 yesterday.

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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/tech-stack 2>/dev/null || echo "(not set)"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.claude/skills/security-and-hardening/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security And Hardening

Active Stack

echo "--- Tech Stack ---"
cat .claude/tech-stack 2>/dev/null || echo "(not set)"

Overview

Treat security and compliance as design constraints, not final review polish. Changes to serious software must preserve confidentiality, integrity, auditability, and least privilege.

When To Use

  • Auth or authorization changes; secrets or configuration changes
  • Audited state mutations (e.g. financial state, patient records, legal documents — see domain supplement)
  • New endpoints, external integrations, infrastructure, or IAM changes

When NOT To Use

  • Purely internal non-sensitive refactors with no new data flow or boundary change

Workflow

  1. Read CLAUDE.md and .claude/references/security-checklist.md first.
  2. If a domain supplement exists (e.g. .claude/references/domain-finance.md), load it for domain-specific rationalizations and review questions.
  3. Identify trust boundaries:
    • user input
    • external service input
    • internal privileged operations
  4. Check auth and authorization requirements.
  5. Check PII, secrets, and logging behavior.
  6. Check audit requirements for state changes that require an audit trail.
  7. Check query safety, transaction boundaries, and error exposure.
  8. For infra, check least privilege, blast radius, and secret access scope.
  9. Supply chain — dependency intake. If the diff adds or replaces a third-party dep (any of package.json, *.csproj, Directory.Packages.props, requirements.txt, pyproject.toml, Pipfile, go.mod, Cargo.toml, Gemfile, composer.json), walk the new dep through .claude/references/dependency-intake-checklist.md — scope, maintenance, size, security, license. Two Poor ratings block; one Poor requires written override. Cite concrete evidence (CVE id, last-release date, license SPDX) per Poor rating.
  10. If a requirement is unclear, stop and ask rather than guessing.

Rules

  • No secrets in code or logs.
  • No unaudited state mutation where the domain requires audit trails.
  • No trust in external input without validation.
  • No wildcard IAM/resource access without explicit justification.
  • No new third-party dep that fails the 5-criteria intake gate (.claude/references/dependency-intake-checklist.md).

Read the full file on GitHub · 83 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. yesterday Changed · -2 lines e1482f123c23
  2. 10d ago First seen · 85 lines · 37 tokens per session scan A f45fce22cd0e

Subscribe to this mod's changes

security-and-hardening is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 864 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). 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