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.
npx skills add HawkannG/Claude-Warden --skill warden-policygit clone --depth 1 https://github.com/HawkannG/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-policy)<a href="https://agentmods.dev/skills/hawkanng/claude-warden/warden-policy"><img src="https://agentmods.dev/badge/skills/hawkanng/claude-warden/warden-policy/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-policy"><img src="https://agentmods.dev/badge/skills/hawkanng/claude-warden/warden-policy.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 | $0.00018 | $0.03378 |
| Opus 5 | $0.00009 | $0.01689 |
| Sonnet 5 | $0.00004 | $0.00676 |
| Haiku 4.5 | $0.00002 | $0.00338 |
Grade A, and why
warden-policy 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.
How it starts
The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Warden Policy — Constitution for AI-Assisted Project Governance
Version: 2.0 Type: Constitution (highest governance authority) Owner: Human ONLY — AI may never modify this file Max Size: 400 lines (this file) | 300 lines (directives) | 80 lines (CLAUDE.md)
0. Philosophy
AI coding assistants are powerful but stateless. They forget rules, create drift, and accumulate entropy over long sessions. This policy creates a structural immune system — governance artifacts that persist even when the AI's context does not.
Four layers of governance exist:
| Layer | Purpose | Mechanism |
|---|---|---|
| Native protection | Block edits to governance files | permissions.deny in settings.json |
| Soft governance | Tell the AI what to do | .md files (this policy + rules) |
| Active governance | Make the AI confirm before acting | CLAUDE.md checklist + recursive output rules |
| Hard governance | Catch violations mechanically | PreToolUse/PostToolUse hooks, linters, CI checks |
Soft governance alone is insufficient. AI can choose to ignore documentation. This policy is the foundation, but enforcement tooling (hooks, folderslint, ls-lint, CI pipeline checks, and the Warden audit tool) is the mechanism that makes it stick.
1. Governance Hierarchy
Plugin (skills/*/SKILL.md): ← Governance Rules (auto-loaded)
├── policy/SKILL.md ← Constitution (this file)
│ Human-owned. Defines all policy areas.
│ AI may NEVER edit.
├── workflow/SKILL.md ← Development Workflow
├── architecture/SKILL.md ← Project Structure
├── feedback/SKILL.md ← Feedback Loop
├── security/SKILL.md ← Security & Privacy
└── second-opinion/SKILL.md ← Rabbit Hole Diagnostic
Plugin (scripts/): ← Enforcement Hooks
└── warden-*.sh Hard enforcement via Claude Code hooks
User Project (.claude/): ← User-Owned Files
├── CLAUDE.md ← Operating Instructions (optional)
│ Short index (~50 rules max).
│ Human-owned. AI may suggest changes.
├── rules/ ← Additional Rules (as needed)
│ └── feedback.md AI writes findings here.
│ Human reviews and adjusts policy.
├── warden.config.sh ← User Configuration (optional)
└── settings.json ← permissions.deny for native protection
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.
- 11d ago First seen · 343 lines · 18 tokens per session scan A e3ad7755d98c
warden-policy is a skill published in the GitHub repository HawkannG/Claude-Warden (2 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 3,378 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.
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-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-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-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.