dforge
dforge is a Claude Code plugin that implements a multi-tier execution framework with scored tasks, criteria-based review, and role-specific agents (7 execution implementers, 4 read-only judges/scouts, and 9 reserve agents) orchestrated by a four-axis rubric and escalation ladder. It handles cost optimization through handoff budgeting, keeps execution on Sonnet-class models by default with Opus reserved for escalation, routes plan defects to a dedicated judge, and integrates with Codex for native execution with read-only reviewer contexts.
Install
Source: https://github.com/darkraise/darkraise-ai-plugins/tree/HEAD/plugins/dforge
What it's made of
20 agents · 24 skills · 4 hooks
- Commands
- 0
- Agents
- 20
- Skills
- 24
- MCP servers
- 0
- Hooks
- 4 · SessionStart, Stop, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
bash- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (darkraise).