Template for AI-native development: Claude Code, OpenCode, Codex and Gemini CLI from one config, intent→spec→plan in CI, eval-gated merges, and the shared fawkes-space devcontainer
This repository also configures its own agents. See what uFawkesAI tells them →
Agent Claude CodeCodex
Implements a planned feature: writes code, manifests, and tests against a committed plan.md. Use when plan.md exists and the work is scoped. Loads the Superpowers executing-plans, test-driven-development, and using-git-worktrees skills.
Agent Claude CodeCodex
Runs the repository and its delivery surfaces: commits, branches, PRs, releases, and the scheduled DORA snapshot. Use for anything that changes repo or release state.
Agent Claude CodeCodex
Turns an intent into committed intent.md, spec.md, and plan.md. Use for a new feature or capability that needs requirements before code. Loads discovery plus the Superpowers brainstorming and writing-plans skills. Writes no implementation code.
Agent Claude CodeCodex
Proves the work is correct rather than merely reported. Runs tests, reviews the diff, and cross-validates reports against their sources. Blocks progression on any unproven claim.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: