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.
/plugin marketplace add HawkannG/Claude-Warden/plugin install claude-wardenWrote 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.
[](https://agentmods.dev/skills/hawkanng/claude-warden/warden-setup)<a href="https://agentmods.dev/skills/hawkanng/claude-warden/warden-setup"><img src="https://agentmods.dev/badge/skills/hawkanng/claude-warden/warden-setup/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.
<a href="https://agentmods.dev/skills/hawkanng/claude-warden/warden-setup"><img src="https://agentmods.dev/badge/skills/hawkanng/claude-warden/warden-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00648 |
| Opus 5 | $0.00013 | $0.00324 |
| Sonnet 5 | $0.00005 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade B, and why
warden-setup scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
bash "$(find ~/.claude/plugins/cache -path '*/claude-warden/*/scripts/warden-setup.sh' 2>/dev/null | head -1)" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: Initialize Claude Warden in a project — creates governance files, seeds deny entries, and migrates from curl-install How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warden Project Setup
Run this skill when setting up Warden in a new project or migrating from the old curl-installer.
What It Does
- Fresh projects: Creates
.claude/CLAUDE.md,.claude/rules/,docs/SESSION-LOG.md, and seeds deny entries in.claude/settings.json - Migration: Detects old curl-install artifacts (
.claude/hooks/,.claude/VERSION,.claude/config/), removes them, cleans stale hook/deny entries fromsettings.json, and preserves user files
Instructions for Claude
When the user invokes /warden-setup or asks to set up Warden in their project:
Step 1: Run the setup script
Find and run the setup script. Try these in order:
# Option 1: Plugin env var (set during hook execution)
bash "$CLAUDE_PLUGIN_ROOT/scripts/warden-setup.sh"
# Option 2: Find in plugin cache (always works)
bash "$(find ~/.claude/plugins/cache -path '*/claude-warden/*/scripts/warden-setup.sh' 2>/dev/null | head -1)"
This runs against $CLAUDE_PROJECT_DIR by default. The script is idempotent — safe to run multiple times.
Available flags:
--force— Overwrite existing governance files (default: skip existing)--skip-deny— Don't add deny entries to settings.json
Step 2: Report results
Tell the user what was created, skipped, or migrated. The script outputs this information.
Step 3: Guide next steps
After setup completes, tell the user:
-
Edit
.claude/CLAUDE.md— This is a human-only file (protected by hooks and deny entries). Fill in project name, stack, current phase, and constraints. The template has placeholder sections to complete. -
Customize config (optional) — Create
.claude/warden.config.shto override defaults:# Example: customize protected files and directory rules PROTECTED_FILES=(".claude/CLAUDE.md" ".claude/rules/*.md" ".claude/settings.json") FORBIDDEN_DIRS=("temp" "tmp" "misc" "stuff" "old" "backup") MAX_DIRECTORY_DEPTH=5 -
Restart Claude Code — New deny entries and governance files take effect on next session.
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.
- 9d ago First seen · 65 lines · 26 tokens per session scan B a9b44e3a673b
warden-setup is a skill published in the GitHub repository HawkannG/Claude-Warden (2 stars, last pushed 6mo ago), licensed MIT. It adds 26 tokens to every session and 648 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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…
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…
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…
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…
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.