ForgeDock

Autonomous software development for Claude Code.

ForgeDock turns every bug found, every fix shipped, and every review finding into structured context that makes the next agent smarter. It catches integration bugs that code review can't see — missing route registrations, env vars present in CI but absent in deploy, Docker permission mismatches, sibling code paths left unfixed. Every finding feeds back as a prevention rule for future builds. After thousands of issues on production codebases, the system catches bugs before they reach a testing branch.

     
 

15+ issues orchestrated in parallel — investigated, built, reviewed, and shipped autonomously.

AI coding agents forget everything between sessions. They re-investigate the same bugs, miss context from past PRs, and make mistakes that were already caught and fixed last week. There's no institutional memory.

ForgeDock fixes this by using GitHub itself as the memory layer. Every pipeline stage writes structured FORGE: annotations to issues and PRs. Every downstream agent reads them. When a new session starts — even after Claude's context resets — the agent queries GitHub and picks up exactly where the last one left off.

ForgeDock is not another AI coding agent. It's a set of prompt-engineered command specs (.md files) that run inside Claude Code. No new runtime, no separate process, no vendor lock-in beyond what you already use.

Cost note: ForgeDock itself is free and open-source. It orchestrates Claude Code sessions, so you pay your normal Anthropic API usage. A typical /work-on run on a straightforward bug uses roughly the same tokens as a 15–20 minute manual Claude Code session.

FORGE:INVESTIGATOR  →  CONFIRMED. All 27 command spec files (848KB) load into
                        context at session start via symlinks. ~200K tokens wasted.

FORGE:CONTRACT      →  Replace symlink-based install with stub-file pattern.
                        Installer parses frontmatter, writes minimal stubs.

FORGE:CONTEXT       →  Issue #577: install() had overly broad catch{} — fixed to
                        check err.code === 'ENOENT'. Issue #587: Windows writes
                        regular files, not symlinks — keep both paths working.

FORGE:ARCHITECT     →  3 new functions in bin/forgedock.mjs: parseFrontmatter(),
                        generateStubContent(), updated install() flow.

FORGE:BUILDER       →  Branch feat/stub-install-pattern-619, 1 file changed.

FORGE:REVIEW        →  Auto-merged to staging.

FORGE:TRAJECTORY    →  Full audit trail recorded.

Requirements: Node.js 18+, Claude Code, GitHub CLI (gh), and yq (YAML parser used by pipeline commands to read forge.yaml)

# Install pipeline commands
npx forgedock

# Generate config for your repo
npx forgedock init

This symlinks 25+ pipeline commands into ~/.claude/commands/ and generates a forge.yaml config in your project root. That's it — open Claude Code and run /work-on #42.

/plugin marketplace add RapierCraftStudios/ForgeDock
/plugin install forgedock@forgedock

npx forgedock update       # Pull latest commands
npx forgedock uninstall    # Remove all ForgeDock commands from ~/.claude/commands/
npx forgedock help         # Show all available commands

/forgedock-init            # Guided config walkthrough — scans your repo, queries GitHub, auto-fills forge.yaml

Issue → Investigate → Architect → Build → Quality Gate → Review → Merge
              ↓            ↓         ↓          ↓            ↓
        writes to     reads from  reads from  reads from   writes to
         GitHub        GitHub      GitHub      GitHub       GitHub

Each stage writes a structured annotation (<!-- FORGE:INVESTIGATOR -->, <!-- FORGE:CONTRACT -->, etc.) to the GitHub issue or PR. Each downstream stage reads what came before. The gh CLI is the query interface.

Labels track workflow state (workflow:investigating, workflow:building, workflow:in-review, workflow:merged). The pipeline resumes from whatever state GitHub says it's in — restart-safe by design.

npx forgedock uninstall

Removes all ForgeDock command symlinks from ~/.claude/commands/. Your forge.yaml config and any FORGE: annotations on GitHub issues/PRs are left untouched.

• Getting Started in 5 Minutes — install, configure, first pipeline run
• How the Knowledge Graph Works — FORGE annotations, context relay, compaction resilience
• ForgeDock vs. Manual Workflows — structured pipelines vs. ad-hoc prompting
• FORGE Annotation Protocol — open standard spec for AI context passing
• Command Reference — all 25+ commands with usage and examples

PRs welcome. Every change goes through a PR, tested against 3+ scenarios, using conventional commits (fix(command):, feat(command):, refactor(command):).

ForgeDock uses a dual-licensing model:

• AGPL-3.0 — free to use, modify, and distribute for open-source and personal use. If you modify ForgeDock and offer it as a service (including over a network), you must open-source your modifications under AGPL-3.0.

• Commercial License — for organizations that need to use ForgeDock in proprietary workflows or products without AGPL-3.0 copyleft obligations. Contact RapierCraft Studios to obtain a commercial license.

The open-source core remains free under AGPL-3.0. The commercial license is an exception for customers who cannot meet the copyleft requirements.