warrant-policy-author

warrant-policy-author is a skill for Claude Code from rmanish2000-del/warrant-mcp. It costs 126 tokens per session (1,969 once invoked), scanned A, original, MIT.

A writing guide for creating `.warrant/policy.md`, a plain-English file describing what an AI agent may do in a project. It shapes the wording for warrant-mcp's review process but does not enforce the rules itself.

In plain words
What is it for?
Use it to create or edit rules about an agent's permitted actions, then submit the resulting policy to warrant-mcp for review.
Why use it?
It helps turn project safety requirements into policy text while making clear that only warrant-mcp's review and enforcement system can approve and enforce them.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event.

Good fit Use it to create or edit rules about an agent's permitted actions, then submit the resulting policy to warrant-mcp for review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rmanish2000-del/warrant-mcp/warrant-policy-author
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 rmanish2000-del/warrant-mcp --skill warrant-policy-author
Clone the repo
git clone --depth 1 https://github.com/rmanish2000-del/warrant-mcp

Made for: Claude Code.

Its marketplace also offers this one on its own, as the plugin warrant-policy-author/plugin install warrant-policy-author after adding the marketplace above.

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 warrant-policy-author

README.md
[![agentmods](https://agentmods.dev/badge/skills/rmanish2000-del/warrant-mcp/warrant-policy-author/github.svg)](https://agentmods.dev/skills/rmanish2000-del/warrant-mcp/warrant-policy-author)
Your own site
<a href="https://agentmods.dev/skills/rmanish2000-del/warrant-mcp/warrant-policy-author"><img src="https://agentmods.dev/badge/skills/rmanish2000-del/warrant-mcp/warrant-policy-author/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 warrant-policy-author

Your own site · 80×15
<a href="https://agentmods.dev/skills/rmanish2000-del/warrant-mcp/warrant-policy-author"><img src="https://agentmods.dev/badge/skills/rmanish2000-del/warrant-mcp/warrant-policy-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,969 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 $0.00126 $0.01969
Opus 5 $0.00063 $0.00984
Sonnet 5 $0.00025 $0.00394
Haiku 4.5 $0.00013 $0.00197

Measured 12d ago against content hash a7bb21739e98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

warrant-policy-author 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 12d 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/warrant-policy-author/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing a warrant-mcp policy

You are helping a human write .warrant/policy.md — the plain-English policy that warrant-mcp compiles into enforceable clauses. Your output is policy text and understanding, nothing else.

Hard constraints — read these as rules for yourself

  1. This skill never enforces anything. It writes policy text. Enforcement is the PreToolUse hook and the deterministic engine. A skill is instructions a model may ignore — which is exactly what enforcement must not be. Never present anything you write as active or protective until the user has run warrant-mcp review and accepted the result.
  2. Never claim a sentence will compile. Only warrant-mcp review can say that. You may say a sentence is shaped to map onto a named rule type; the compiler is the authority. If review refuses a sentence this skill produced, the skill was wrong and the refusal is right — say so, read the refusal's guidance, and rewrite.
  3. Never edit compiled artifacts. Do not touch policy-compiled.json, policy-compiled.pending.json, or anything under ~/.warrant/. The only file you write is .warrant/policy.md.
  4. Never put a regex, glob, or wildcard in a policy sentence. The rule set is pure data by design; suggest concrete names instead.

Step 1 — Interview, briefly

Ask three questions (adapt wording; keep it short):

  1. What is this project, and what is the agent for? (A test-writing agent needs write access to tests/; a research agent may need no writes at all. The answer shapes which rules make sense.)
  2. What would you never want touched? (Files, directories, branches. Listen for: secrets files, data directories, infra/prod paths, .git.)
  3. What should the agent never run, and where may it talk to? (Commands and their flags; hosts. If they say "nothing dangerous", ask for the two or three commands they actually fear — the compiler will not guess them.)

Do not over-interview. Three answers are enough to draft; the review loop exists for refinement.

Read the full file on GitHub · 148 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 148 lines · 126 tokens per session scan A a7bb21739e98

Subscribe to this mod's changes

warrant-policy-author is a skill published in the GitHub repository rmanish2000-del/warrant-mcp (1 stars, last pushed 18d ago), licensed MIT. It adds 126 tokens to every session and 1,969 once invoked, about $0.0006 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

constitutional-ai

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

davila7/claude-code-templates · 58 tokens

security-compliance

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

sangrokjung/claude-forge · 56 tokens

aenderungsvorbehalt-308

Für Änderungsvorbehalt 308: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 41 tokens

agb-begriff-vorformuliert-305

Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.

Klotzkette/claude-fuer-deutsches-recht · 68 tokens

beweislast-und-zugang-309

Für Beweislast und Zugang 309: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Beweislast- und Substantiierungsmatrix.

Klotzkette/claude-fuer-deutsches-recht · 43 tokens

agb-pruefung-kaltstart

Für AGB Prüfung Kaltstart: routet Rolle, Frist, Unterlagen und Fachschritt; Ergebnis: Tatbestands- oder Anspruchsmatrix.

Klotzkette/claude-fuer-deutsches-recht · 41 tokens