Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Harden

ASecurity

Hardens the runtime and perimeter — security headers/CSP, TLS/HSTS, proxy (Caddy/nginx) config, rate/body limits, WebSocket protections, Docker network/container hardening, CI permissions, secrets hygiene; verifies with live curl/scanner output; writes docs/security/hardening-checklist.md.

3 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentsbashangulardockergitsecurity

Works with

cli

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add gonimar/claude-web-studio --skill harden --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Harden?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Harden
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gonimar-harden/badge)](https://www.skillsdirectory.com/skills/gonimar-harden)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: harden
description: "Hardens the runtime and perimeter — security headers/CSP, TLS/HSTS, proxy (Caddy/nginx) config, rate/body limits, WebSocket protections, Docker network/container hardening, CI permissions, secrets hygiene; verifies with live curl/scanner output; writes docs/security/hardening-checklist.md."
argument-hint: "[full | headers | tls | proxy | docker | ci | secrets] [--apply]"
user-invocable: true
allowed-tools: Read, Glob, Grep, Bash, Write, Edit, Task, AskUserQuestion
model: sonnet
agent: network-security-engineer
---

# Harden

Reply in the project conversation language (CLAUDE.md → Language); code, identifiers, paths and commit messages stay in English.

`stack-reference/security-standards.md`, `security-baseline.md` (headers, network), rules `rules/ci-docker.md`, `rules/security-sensitive.md`.

## Phase 1: Inventory
Proxy configs — in this repository or in the **Infra repo / Proxy config** from `technical-preferences.md` (Infrastructure) when the proxy lives elsewhere; compose/Dockerfile, workflows, where TLS terminates, current headers (`curl -sI <url>` on dev/staging/prod with consent). No infra repo declared and no proxy config here → say so: the checklist can only be verified live, not fixed, and `/setup-stack`/`/adopt` records the field.

## Phase 2: Checklist
Headers (HSTS, CSP nonce/strict-dynamic — mind Angular `ngCspNonce`/Nuxt, nosniff, Referrer-Policy, Permissions-Policy, COOP/CORP), cookie flags; TLS profile; `server_tokens`/`limit_req`/`client_max_body_size`/timeouts; WebSocket Origin/limits; Docker: networks, non-root, `cap_drop`, `read_only`, pins, health checks; CI `permissions`; secrets (`.env` ignored, gitleaks). Per item — status and a verification command.
**`secrets` mode (rotation checklist)** — an inventory, never the values: every secret the project uses, from the deploy contract's Prerequisites & secrets, `.env.example`, compose `environment:`/`env_file:`, workflow `secrets.*` references and the platform UI names; per secret: where it lives (platform env, `~/.config/<project>/*.env`, CI secret, registry token), which component reads it, the provider's rotation steps (issue new → deploy → verify → revoke old), the last rotation date if recorded. Then the checks: `gitleaks` / `git log -p -S` for the old value pattern (never the value itself in the command line), no secret in images (`docker history`, build args), CI `permissions` least-privilege, `.env` ignored. Output: the rotation table + the order to rotate in (dependencies first) + the verification per secret; written into `docs/security/hardening-checklist.md` § Secrets. Trigger: a leak (`/incident`), a departure, quarterly.

## Phase 3: Changes (`--apply` or with consent)
Show config diffs — in the infra repo when declared ("May I write [infra repo path/file]?"), otherwise the exact snippet for the owner of the proxy; validate with `nginx -t`/`caddy validate`/`docker compose config`; repeat `curl -I` — before/after output. The live headers are the evidence in both cases.

## Phase 4: Write
"May I write `docs/security/hardening-checklist.md`?" — one `AskUserQuestion`: write (Recommended) · show the draft/diff first · not now After the "write" answer: `touch .claude/.write-consent` (rule 7 — the consent-guard hook checks the marker).

Verdict: `HARDENED` | `PARTIAL (open: …)`. Next step — one `AskUserQuestion`: `/security-audit quick` (Recommended) · `/pentest` (optional) · stop here.

Attribution

gonimargonimar
View sourceMore from gonimar →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →