berean

berean is a plugin for Claude Code from wildcat-finance/skills. Its manifest loads nothing; the 1 skill it bundles cost 109 tokens per session together, scanned A, original, Apache-2.0.

A release format for coding agents that pins evidence to an exact digital fingerprint and supports citations tied to specific blocks of text. It also includes evaluated refusals, meaning refusal behavior can be tested against set criteria.

In plain words
What is it for?
Use it to package agent releases, produce exact citations, restrict reads to defined text blocks, and evaluate refusal responses.
Why use it?
It makes an agent's cited material easier to verify and helps check whether refusals meet the expected standard.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add wildcat-finance/skills
agentmods
npx agentmods add plugins/wildcat-finance/skills/berean
Clone the repo
git clone --depth 1 https://github.com/wildcat-finance/skills

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 berean

README.md
[![agentmods](https://agentmods.dev/badge/plugins/wildcat-finance/skills/berean.svg)](https://agentmods.dev/plugins/wildcat-finance/skills/berean)
Your own site
<a href="https://agentmods.dev/plugins/wildcat-finance/skills/berean"><img src="https://agentmods.dev/badge/plugins/wildcat-finance/skills/berean.svg" alt="Measured on agentmods" 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 cost 109 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

berean 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 5d 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.

plugins/berean/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "berean",
  "displayName": "Berean",
  "version": "0.1.2",
  "description": "Digest-pinned agent releases with byte-exact citations, block-bound reads and evaluated refusals.",
  "author": {
    "name": "Wildcat Labs",
    "url": "https://wildcat.finance"
  },
  "homepage": "https://github.com/wildcat-finance/skills/tree/main/plugins/berean",
  "repository": "https://github.com/wildcat-finance/skills",
  "license": "Apache-2.0",
  "keywords": [
    "agents",
    "evidence",
    "citations",
    "releases",
    "evaluation"
  ],
  "skills": "./skills/"
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 109 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. 5d ago First seen · 22 lines scan A 9653fe48fba4

Subscribe to this mod's changes

berean is a plugin published in the GitHub repository wildcat-finance/skills (12 stars, last pushed today), licensed Apache-2.0. 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 2026-08-30.

Related

Other plugins, from other repositories

atlas-publish

Takes the open PRs of the Atlas/Bella monorepo to a registered draft release on either the over-the-air or the App Store lane, classifying between them from the expo-updates native fingerprint rather than from intent — ios.buildNumber sits inside that fingerprint, so a buildNumber bump alone forces a store release.…

fledgeling-co/fledgeling-plugins · not measured

charon

Ferries a GitHub PR to merge without waiting forever: an honest snapshot-not-block loop that fixes CI, repairs conflicts, version-checks reviewer suggestions, and never says 'just wait'.

ANcpLua/ancplua-claude-plugins · not measured

beecount-release

BeeCount 全家桶发版流水线:双仓 tag 触发 CI、changelog 双格式、官网同步、视频文案收尾,带版本号与发布范围的用户确认门。.

TNT-Likely/honeycomb · not measured

ooda-loop marketplace

Plugin marketplace listing 1 plugin: ooda-loop.

mataeil/OODA-loop · not measured

utility-tools

Developer productivity tools for Claude Code — generate McKinsey-style HTML slide decks from marketing strategies, automate software releases with version bumping, changelog generation, git tagging, and GitHub release publishing. 3 skills for teams shipping fast.

pawbytes/skill-suites · not measured

essentials

Essential shipping workflow — group a dirty working tree into clean commits, push the branch, and open a senior-engineer-quality GitHub PR with auto-applied labels and "might address #X" issue links.

AgentSystemLabs/essentials · not measured