warden-architecture

warden-architecture is a skill for Claude Code from HawkannG/Claude-Warden. It costs 17 tokens per session (1,982 once invoked), scanned A, original, MIT.

A project-folder policy template that defines which directories and file locations are allowed, along with depth limits and forbidden patterns.

In plain words
What is it for?
It is for setting directory rules that an AI agent, hooks, or other checks can use while working in a project.
Why use it?
It reduces clutter and prevents files from being created in unauthorized places.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the claude-warden plugin — 7 skills, 4 hooks shipped together

Good fit It is for setting directory rules that an AI agent, hooks, or other checks can use while working in a project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hawkanng/claude-warden/warden-architecture
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add HawkannG/Claude-Warden --skill warden-architecture
Clone the repo
git clone --depth 1 https://github.com/HawkannG/Claude-Warden

Made for: Claude Code.

Or install claude-warden, the plugin that ships this one along with the rest of its 7 skills, 4 hooks.

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 warden-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/hawkanng/claude-warden/warden-architecture/github.svg)](https://agentmods.dev/skills/hawkanng/claude-warden/warden-architecture)
Your own site
<a href="https://agentmods.dev/skills/hawkanng/claude-warden/warden-architecture"><img src="https://agentmods.dev/badge/skills/hawkanng/claude-warden/warden-architecture/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 warden-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/hawkanng/claude-warden/warden-architecture"><img src="https://agentmods.dev/badge/skills/hawkanng/claude-warden/warden-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,982 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 $0.00017 $0.01982
Opus 5 $0.00009 $0.00991
Sonnet 5 $0.00003 $0.00396
Haiku 4.5 $0.00002 $0.00198

Measured 11d ago against content hash d75c228ea673, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

warden-architecture 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 11d 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.

skills/warden-architecture/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Directory Structure Template

Policy Area: ARCH — Architecture Version: 2.0 Last Reviewed: 2026-02-11 Owner: Human+AI References: workflow.md Enforcement: Active (CLAUDE.md rule) + Hard (hooks)


Purpose

This is a TEMPLATE for projects using Warden. Customize it for your project's specific directory structure and naming conventions.

This directive defines the only approved directories and file locations for your project. Any file or directory not listed here is unauthorized. The AI must consult this directive before creating any file and must update this directive (with human approval) before creating any new directory.

For the Warden Framework's own structure, see the "Framework Directory Structure" section in README.md.


Instructions

INS-DA1-001: Approved Directory Tree

IMPORTANT: This is an EXAMPLE structure. Replace it with your project's actual directories. The following shows common patterns for different project types — choose one or adapt as needed.

Option 1: Simple CLI/Library Project

/project-root/
├── src/                     # Source code
│   ├── core/               # Core functionality
│   ├── utils/              # Utilities (max 5 files)
│   └── cli/                # CLI interface (if applicable)
├── tests/                   # Tests mirror src/ structure
│   ├── test_core/
│   └── test_utils/
├── docs/                    # Documentation (non-governance)
└── .claude/                     # Governance files (see .claude/rules/policy.md)

Option 2: Web Application (Frontend + Backend)

/project-root/
├── backend/
│   ├── app/
│   │   ├── models/         # Data models
│   │   ├── routes/         # API endpoints
│   │   ├── services/       # Business logic
│   │   └── core/           # Config, middleware
│   ├── tests/              # Mirrors backend/app/ structure
│   └── requirements.txt
├── frontend/
│   ├── src/
│   │   ├── components/     # UI components
│   │   ├── pages/          # Page components
│   │   ├── services/       # API client
│   │   └── utils/          # Utilities (max 5 files)
│   └── package.json
├── scripts/                 # Build/deploy scripts
├── docs/                    # Documentation
└── .claude/                     # Governance files (see .claude/rules/policy.md)

Read the full file on GitHub · 217 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. 11d ago First seen · 217 lines · 17 tokens per session scan A d75c228ea673

Subscribe to this mod's changes

warden-architecture is a skill published in the GitHub repository HawkannG/Claude-Warden (2 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 1,982 once invoked, about $0.0001 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

r3f-best-practices

React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.

zebbern/claude-code-guide · 74 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

offensive-c2-frameworks

Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…

SnailSploit/Claude-Red · 250 tokens

offensive-crypto-attacks

Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…

SnailSploit/Claude-Red · 261 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

code-mate-antigravity

Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.

CherryHQ/cherry-studio · 43 tokens