barmkin-mod

A Claude Code mod in samfrmr/barmkin-mod

Claude Code mods security layer: secret redaction, untrusted-content taint with a Rule-of-Two egress gate, skill inline-shell mediation guard, MCP tool-poisoning guard, skill-content screen, agent-to-agent firewall, and a Jev System One classifier gateway with an explanation surface.

barmkin-mod reaches L3 (network) by its classified calls and passed claude plugin validate on Claude Code 2.1.302.

Events hooked: 14
API methods referenced: 11
Access from classified calls: L3, network: network, reads settings, draws
Unclassified calls: 2 ($.state.get, $.state.set), full access unknown
Static scan, not a runtime test

To install it, open the repository and follow the author’s setup instructions. Mods need Claude Code 2.1.287 or later.

Access

L3 Uses the networkother: $.state.get, other: $.state.set, network, reads settings, draws

Validation

Passed on Claude Code 2.1.302

View the source on GitHub Back to the list

What the scan recorded

Observed events: every prompt, compaction, every tool call, /"^mcp__"/ calls, Bash|PowerShell|WebFetch|WebSearch|Monitor|Edit|Write|MultiEdit|NotebookEdit calls, WebFetch|WebSearch calls, Read calls, Skill calls, every skill, subagent spawns
Hooks: session.start, prompt.submit, session.compact, session.end, tool.describe {tool=/"^mcp__"/}, tool.call, tool.call {tool=/"^mcp__"/}, tool.call {tool=Bash|PowerShell|WebFetch|WebSearch|Monitor|Edit|Write|MultiEdit|NotebookEdit}, tool.call {tool=WebFetch|WebSearch}, tool.call {tool=Read}, tool.call {tool=Skill}, tool.check {tool=Bash|PowerShell|Monitor}, skill.prompt, prompt.attachment {type=skill_listing}, session.receive, session.send, agent.spawn, ui.render {component=AbovePrompt}, ui.render {component=PromptHint}, command.run {command=barmkin-mod-status}, command.run {command=barmkin-mod-clear-taint}
API calls: $.clock.after, $.command.register, $.http.fetch, $.session.cwd, $.session.version, $.settings.read, $.state.get, $.state.set, $.ui.log, $.ui.notice, $.ui.resolve
Validation on 2.1.302: Passed
Scanned revision: 0ded341bef08

These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.

Badge for your README

Authors can show the latest scan result in their README. Each badge links to this page.

[![reach](https://raw.githubusercontent.com/karanb192/awesome-claude-code-mods/main/badges/samfrmr--barmkin-mod--barmkin-mod-reach.svg)](https://mods.aidojo.si/mods/samfrmr--barmkin-mod--barmkin-mod/)
[![validates](https://raw.githubusercontent.com/karanb192/awesome-claude-code-mods/main/badges/samfrmr--barmkin-mod--barmkin-mod-validates.svg)](https://mods.aidojo.si/mods/samfrmr--barmkin-mod--barmkin-mod/)