By cooperacode
AI-assisted agile artifact generation organized around a Strategic → Product → Tactical work item hierarchy. Manages a knowledge wiki and produces engineering artifacts (briefs, requirements, ADRs, diagrams, user stories) from ingested sources.
Set the language for artifact generation and user interactions. Supported: en (English), pt-BR (Brazilian Portuguese).
Generate a software engineering artifact for the active work item. Routes to the correct artifact type based on the hierarchy level set in .env.
Create or select the active work item. Creates a new work item or switches focus to an existing one, writing the .env context file used by all other commands.
Add new sources to the wiki, creating and updating pages as needed. Always update the index and log. Default is non-interactive. Pass -buddy for step-by-step confirmation.
Scan the wiki for structural, factual, and navigational problems — and fix what you can, flag what you cannot.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
An AI-assisted knowledge and artifact pipeline for engineering teams — traceable from source document to shipped user story.
forge is an AI plugin for Claude Code and VS Code that turns a plain git repository into a structured knowledge base and artifact generation pipeline. Teams register work items, drop source documents (specs, meeting notes, PDFs, emails) into a folder, and the plugin ingests them into cross-linked wiki pages — then generates software engineering artifacts that build progressively on each other: briefs, quality attributes & constraints, ADRs, feature lists, diagrams, and user stories.
Every artifact traces back to a source document. Every decision can be explained.
The work item hierarchy mirrors what teams already use in Jira, Azure DevOps, and SAFe — Strategic (Themes, Initiatives), Product (Epics, Features), and Tactical (User Stories, Tasks, Bugs). Artifacts generated at the strategic level automatically propagate as constraints into product-level work; product artifacts flow into tactical ones. The knowledge travels with the hierarchy.
New to forge? Start with the Quick Start.
flowchart LR
A([Team]) -->|/focus| B[Register<br/>work item]
B --> C[(forge.yaml<br/>+ .env)]
C --> D[Drop files<br/>into input/]
D -->|/ingest| E[Knowledge<br/>wiki]
E -->|/query| F([Answer<br/>with citations])
E -->|/lint| G([Health<br/>check])
E -->|/draft| H([Engineering<br/>artifact])
.env.
input/ (Markdown, PDF, plain text, images).
feature-list feeds the Feature's feature-detail, which feeds individual user-story files at Tactical level.
| Guide | Description |
|---|---|
| Quick Start | End-to-end case walkthrough from Strategic Initiative to Tactical user stories |
| How To: Create Work Items | Create and select work items; understanding the hierarchy |
| How To: Create and Maintain a Wiki | Ingest sources, query the wiki, and run health checks |
| How To: Generate Artifacts | Generate briefs, requirements, ADRs, diagrams, and user stories |
| Research & Documentation | Deep-dive reference for every command, skill, and concept |
npx claudepluginhub cooperacode/forgeA persistent LLM-maintained wiki for your knowledge base. Ingest sources, query your knowledge, and lint for consistency.
Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete Claude Code configs for mobile development - Android, iOS, and Kotlin Multiplatform
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex and gemini CLIs when installed) to get diverse perspectives on coding problems