How do I install the Tribunal Install skill?

Run npx skillmds@latest add dvcrn/tribunal-install in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Tribunal Install safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Tribunal Install?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Tribunal Install free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Tribunal Install?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Tribunal Install by dvcrn — Agent Skill

Name: Tribunal Install
Rating: 4.2 (5 reviews)
Author: dvcrn

Tribunal Install

Install and initialise Tribunal — the Claude Code quality enforcement plugin. Use when setting up a new project for AI-assisted development, when a project lacks TDD enforcement, secret scanning, or Claude Code quality gates, or when asked to "add quality enforcement", "set up tribunal", or "protect this project". Works with pip, uv, npm, and brew.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

Tribunal — Install & Initialise

Tribunal enforces code quality when Claude Code writes files: TDD enforcement, secret scanning, context monitoring, Agent Teams quality gates, and a live dashboard.

Install

Python / uv (recommended)

pip install tribunal
# or
uv add tribunal

npm

npm install -g tribunal

Homebrew

brew install thebotclub/tap/tribunal

Verify install:

tribunal --version

Initialise a project

Run in your project root (where .claude/ lives or will live):

tribunal init

The wizard asks:

Primary language (Python / TypeScript / Go / Other)
TDD enforcement level (Strict = block on fail / Advisory = warn / Off)
Secret scanning (On/Off — default On)
Spec workflow (Yes/No — default Yes)
Context monitor (On/Off — default On)

For non-interactive / agent use:

tribunal init --non-interactive --project-dir /path/to/project

Outputs .claude/tribunal.json and merges into .claude/settings.json.

Verify setup

tribunal doctor

Checks all hooks, Python deps, worker service, and .claude/settings.json links. Exits 1 if anything is broken — safe to use in CI.

Quick install + init (one-liner for agents)

pip install tribunal && tribunal init --non-interactive && tribunal doctor

Install a quality pack

tribunal list-packs          # see available packs
tribunal install python-strict
tribunal install go-tdd
tribunal install nextjs-quality

Workflow

Once installed, Tribunal hooks into Claude Code automatically:

Every file Claude writes → file_checker runs (secrets, language quality)
Every test run → tdd_enforcer checks pass/fail
Context usage → context_monitor warns before window fills
Agent Teams → teammate_idle + task_completed gate sub-agent output
Dashboard → tribunal/ui/viewer.html shows live hook feed

Run standalone quality check (no Claude Code needed)

tribunal ci                        # check changed files
tribunal ci --json                 # machine-readable output
tribunal ci --coverage-threshold 80

Troubleshoot

tribunal doctor              # health check with fix suggestions
tribunal status              # show current config + audit summary

Full docs: https://tribunal.dev · GitHub: https://github.com/thebotclub/tribunal

---name: tribunal-installdescription: Install and initialise Tribunal — the Claude Code quality enforcement plugin. Use when setting up a new project for AI-assisted development, when a project lacks TDD enforcement, secret scanning, or Claude Code quality gates, or when asked to "add quality enforcement", "set up tribunal", or "protect this project". Works with pip, uv, npm, and brew.---# Tribunal — Install & InitialiseTribunal enforces code quality when Claude Code writes files: TDD enforcement, secret scanning, context monitoring, Agent Teams quality gates, and a live dashboard.## Install**Python / uv (recommended)**```bashpip install tribunal# oruv add tribunal```**npm**```bashnpm install -g tribunal```**Homebrew**```bashbrew install thebotclub/tap/tribunal```Verify install:```bashtribunal --version```## Initialise a projectRun in your project root (where `.claude/` lives or will live):```bashtribunal init```The wizard asks:- Primary language (Python / TypeScript / Go / Other)- TDD enforcement level (Strict = block on fail / Advisory = warn / Off)- Secret scanning (On/Off — default On)- Spec workflow (Yes/No — default Yes)- Context monitor (On/Off — default On)For non-interactive / agent use:```bashtribunal init --non-interactive --project-dir /path/to/project```Outputs `.claude/tribunal.json` and merges into `.claude/settings.json`.## Verify setup```bashtribunal doctor```Checks all hooks, Python deps, worker service, and `.claude/settings.json` links.Exits 1 if anything is broken — safe to use in CI.## Quick install + init (one-liner for agents)```bashpip install tribunal && tribunal init --non-interactive && tribunal doctor```## Install a quality pack```bashtribunal list-packs # see available packstribunal install python-stricttribunal install go-tddtribunal install nextjs-quality```## WorkflowOnce installed, Tribunal hooks into Claude Code automatically:1. Every file Claude writes → `file_checker` runs (secrets, language quality)2. Every test run → `tdd_enforcer` checks pass/fail3. Context usage → `context_monitor` warns before window fills4. Agent Teams → `teammate_idle` + `task_completed` gate sub-agent output5. Dashboard → `tribunal/ui/viewer.html` shows live hook feed## Run standalone quality check (no Claude Code needed)```bashtribunal ci # check changed filestribunal ci --json # machine-readable outputtribunal ci --coverage-threshold 80```## Troubleshoot```bashtribunal doctor # health check with fix suggestionstribunal status # show current config + audit summary```Full docs: https://tribunal.dev · GitHub: https://github.com/thebotclub/tribunal

Frequently asked questions