agentmods.dev

warrant-review

warrant-review is a plugin for Claude Code from s0fractal/warrant. Its manifest loads nothing; the 1 skill, 1 MCP server it bundles cost 131 tokens per session together, scanned A, original, MIT.

A code-review add-on built around the warrant MCP server, where an agent reviews a pull request and records findings or acceptance as signed Warrant 3 records.

In plain words
What is it for?
It is for reviewing the head version of a pull request, filing review findings, or accepting the change with signed records.
Why use it?
It gives the review decision a recorded, signed form rather than leaving findings or approval only in an informal conversation.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

not rated 5repo 3d ago A scan tokens not measured original MIT

Good fit It is for reviewing the head version of a pull request, filing review findings, or accepting the change with signed records.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add s0fractal/warrant
/plugin install warrant-review
View source ↗ s0fractal/warrant s0fractal.github.io
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.

Clone the repo
git clone --depth 1 https://github.com/s0fractal/warrant

Made for: Claude Code.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/plugins/s0fractal/warrant/warrant-review/github.svg)](https://agentmods.dev/plugins/s0fractal/warrant/warrant-review)
Your own site
<a href="https://agentmods.dev/plugins/s0fractal/warrant/warrant-review"><img src="https://agentmods.dev/badge/plugins/s0fractal/warrant/warrant-review/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-review

Your own site · 80×15
<a href="https://agentmods.dev/plugins/s0fractal/warrant/warrant-review"><img src="https://agentmods.dev/badge/plugins/s0fractal/warrant/warrant-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 1 MCP server cost 131 tokens a session between them.
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.
Security

Grade A, and why

warrant-review 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 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.

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.

integrations/warrant-review/.claude-plugin/plugin.json · 12 lines

What it actually says

{
  "name": "warrant-review",
  "version": "0.2.0",
  "description": "The warrant MCP server and the review skill of the warrant review loop: an agent that holds a reviewer role files findings against a pull request's head version, or accepts it, as signed Warrant 3 records.",
  "author": { "name": "s0fractal", "url": "https://github.com/s0fractal" },
  "homepage": "https://github.com/s0fractal/warrant/tree/master/integrations/warrant-review",
  "repository": "https://github.com/s0fractal/warrant",
  "license": "MIT",
  "keywords": ["warrant", "review", "mcp", "provenance", "agents"],
  "mcpServers": "./mcp.json"
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 131 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 9d ago First seen · 12 lines scan A ed040f844b9b

Subscribe to this mod's changes

warrant-review is a plugin published in the GitHub repository s0fractal/warrant (5 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-11-01.

Building agentsCode reviewai-agentsauditcontent-addresseddecision-recordsed25519provenance
Related

warrant-review compared with plugins from other repositories

warrant-review next to 6 plugins from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
warrant-reviews0fractal/warrantPlugin53d agoMITA—Claude Code
ememVortx-AI/ememPlugin89yesterdayApache-2.0A—Gemini CLI
emem-signerVortx-AI/ememPlugin89yesterdayApache-2.0A—Claude Code
ememVortx-AI/ememPlugin89yesterdayApache-2.0A—Claude Code
ememVortx-AI/ememPlugin89yesterdayApache-2.0A—Gemini CLI
auraNaridon-Inc/auraPlugin4929d agoApache-2.0A—Claude Code
aura-geminiNaridon-Inc/auraPlugin4929d agoApache-2.0A—Gemini CLI