Home/AI Agents/arc-kit
arc-kit logo

arc-kit

tractorjuice/arc-kit

The Enterprise Architecture Governance Harness

GraphCanon updated 3w · GitHub synced 3w

2.1k stars256 forksLast push 3w JavaScript Other

Decision brief

arc-kit provides tools for governing and ensuring compliance in AI coding assistant processes within enterprise settings.

Good fit when

  • When you need to manage the governance and compliance of AI coding assistants in large enterprises.
  • For organizations that require detailed architecture decision records, procurement, and traceability features specifically tailored for AI agents.

Avoid when

  • If your requirement focuses narrowly on programming language support without a significant enterprise architecture governance aspect.
  • Not suitable if your needs are primarily centered around general code quality improvement tools rather than compliance and strategy management for AI assistants.

Observed Jul 15, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Very active (1d since push)
As of 3w
Provenance
Not a fork · Personal account
As of 3w
Security (OSV)
No MCP manifest
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

npm install arc-kit
npm

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Strategy, architecture, delivery, and assurance for AI coding assistants.

Capability facts

CLI
CLI entrypoint

Source: pyproject.toml:[project.scripts] · Jul 27, 2026

MCP server
No MCP server detected

Source: repo_scan · Jul 27, 2026

Languages
javascript, python

Source: github.language+package.json+pyproject.toml · Jul 27, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 27, 2026)

pip install git+https://github.com/tractorjuice/arc-kit.git
Source link

Tags

README

Installation

Claude Code (premier experience) — install the ArcKit plugin (requires v2.1.200+):

First, make sure Claude Code is on the latest version:

claude install latest

Then in Claude Code:

/plugin marketplace add tractorjuice/arckit-claude

Then install from the Discover tab, or via CLI. The marketplace ships 15 plugins — install only the overlays you need:


---

# Install with pip
pip install git+https://github.com/tractorjuice/arc-kit.git

---

# Minimal install (skip docs and guides)
arckit init payment-modernization --ai codex --minimal

---

### On-invoke cost by command

Costs are estimates from the Claude Code tokenizer and may differ from actual usage. Use this table to budget research-heavy multi-command sessions.

| Tier | Range | Commands |
|------|-------|----------|
| Lightweight | <2K | `start`, `init`, `build`, `search`, `impact`, `navigator`, `graph-report`, `framework`, `gov-landscape`, `aws-research`, `azure-research`, `gcp-research` |
| Standard | 2–7K | `customize`, `score`, `principles`, `mermaid-syntax`, `plantuml-syntax`, `architecture-workflow`, `datascout`, `tenders`, `competitors`, `evaluate`, `hld-review`, `mlops`, `devops`, `finops`, `research`, `tcop`, `wardley-mapping`, `template-builder`, `glossary`, `dld-review`, `traceability`, `stakeholders`, `presentation`, `dfd`, `operationalize`, `requirements`, `maturity-model`, `data-model`, `gov-reuse`, `strategy`, `presentation`, `atrs`, `gov-code-search`, `READER-PATTERN` |
| Heavy | 7–15K | `wardley.value-chain`, `gcloud-clarify`, `ai-playbook`, `sow`, `sobc`, `risk`, `secure`, `dpia`, `dos`, `mod-secure`, `plan`, `conformance`, `roadmap`, `health`, `wardley.doctrine`, `wardley.gameplay`, `pages`, `servicenow`, `gcloud-search`, `principles-compliance`, `story`, `wardley`, `wardley.climate`, `data-mesh-contract`, `platform-design`, `adr`, `arckit-build`, `grants` |
| Research-heavy | 15–25K | `service-assessment`, `analyze`, `backlog`, `diagram` |
| Specialist | >25K | `jsp-936` (~60K — MOD JSP 936 AI assurance, defence-only) |

---

### Phase 5: Define Requirements

**`/arckit:requirements`** → Document comprehensive requirements

Create detailed requirements **informed by stakeholder goals** (if SOBC approved):

- Business requirements with rationale
- Functional requirements with acceptance criteria
- Non-functional requirements (performance, security, scalability, compliance)
- Integration requirements (upstream/downstream systems)
- Data requirements (DR-xxx)
- Success criteria and KPIs

---

# Install and create project (3 steps, zero config)
pip install git+https://github.com/tractorjuice/arc-kit.git
arckit init my-project --ai copilot
cd my-project && code .

---

# Install and create project (3 steps, zero config)
pip install git+https://github.com/tractorjuice/arc-kit.git
arckit init my-project --ai codex
cd my-project && codex

---

### Requirements & Data

| Command | Description | Examples | Status |
|---------|-------------|----------|--------|
| `/arckit:requirements` | Create comprehensive business and technical requirements | [v1](https://tractorjuice.github.io/arckit-test-project-v1-m365/#projects/001-exchange-online-migration/ARC-001-REQ-v1.0.md) [v2](https://tractorjuice.github.io/arckit-test-project-v2-hmrc-chatbot/#projects/001-hmrc-chatbot/ARC-001-REQ-v1.0.md) [v3/001](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/001-windows-11-migration-intune/ARC-001-REQ-v1.0.md) [v3/002](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/002-application-packaging-rationalisation/ARC-002-REQ-v1.0.md) [v3/003](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/003-peripherals-update-upgrade/ARC-003-REQ-v1.0.md) [v3/004](https://tractorjuice.github.io/arckit-test-project-v3-windows11/#projects/004-conference-facilities-modernization/ARC-004-REQ-v1.0.md) [v3/005](https://tractorjuice.github.io/arckit-test-project-v3

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.