Production-ready AI development workflow system for Claude Code — skills, CI/CD workflows, memory patterns, guided onboarding, and project scaffolding
This repository also configures its own agents. See what claude-code-framework tells them →
BostonOrange/claude-code-framework
Agent Claude Code
Build phase 1 specialist — creates the file structure, types/interfaces, function signatures, and empty stubs for a planned change. Does not implement logic; produces the skeleton the next phases fill in. Constrained by all relevant .claude/rules/.
BostonOrange/claude-code-framework
Agent Claude Code
Breaks a story or task into atomic, independently-testable steps with explicit sequencing and dependencies. Identifies what can run in parallel and what must happen in order.
BostonOrange/claude-code-framework
Agent Claude Code
Reviews changed code for SOLID principle violations — Open/Closed, Liskov Substitution, Interface Segregation, Dependency Inversion. Cites the solid rule. SRP (the S of SOLID) is owned by purity-reviewer.
BostonOrange/claude-code-framework
Agent Claude Code
Reviews changed dependency manifests, lockfiles, Dockerfiles, and CI workflow files for OWASP A06 (vulnerable components) and A08 (integrity failures). Covers lockfile hygiene, version pinning, CVE reachability, package signing, dev/prod separation, deserialization risks, CI pipeline integrity, build reproducibility…
BostonOrange/claude-code-framework
Agent Claude Code
Decides what tests at what level (unit / integration / e2e / contract / property) for a planned change. Output feeds into the plan so the build phase generates the right tests.
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: