BostonOrange/claude-code-framework

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 →

3Stars on the repository
97Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

BostonOrange/claude-code-framework

Agent Claude Code

Reviews API code for controller/service/repository separation, validation layer placement, error contract consistency, idempotency, and versioning discipline. Cites the api-layering rule. Distinct from api-designer (designs API surface) and api-routes rule (per-route concerns).

not rated 3 3mo ago A 69 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Reviews changed code for layer-dependency violations, cross-module reach, circular dependencies, god modules, public-API leaks, and structural patterns. Cites the architecture-layering rule. Distinct from architect (which plans) — this agent reviews code against architectural rules.

not rated 3 3mo ago A 60 tokens original MIT

build-coordinator

03

BostonOrange/claude-code-framework

Agent Claude Code

Orchestrates build phases sequentially — scaffold → happy-path → edge-case → tests → docs → refactor — using the plan from planner-coordinator. Each phase is one specialist; the coordinator manages sequencing, state, and resumption.

not rated 3 3mo ago A 51 tokens original MIT

code-smell-reviewer

04

BostonOrange/claude-code-framework

Agent Claude Code

Reviews changed code for classic code smells — long methods, magic numbers, primitive obsession, data clumps, feature envy, dead code, comments-as-deodorant, speculative generality. Cites the code-smells rule.

not rated 3 3mo ago A 52 tokens original MIT

complexity-reviewer

05

BostonOrange/claude-code-framework

Agent Claude Code

Reviews changed code for excessive function length, cyclomatic complexity, nesting depth, parameter count, and branch density. Cites the complexity rule.

not rated 3 3mo ago A 35 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Reviews changed code for race conditions, TOCTOU bugs, async discipline, lock discipline, mutable shared state, background-work safety, and channel/queue discipline. Cites the concurrency rule.

not rated 3 3mo ago A 45 tokens original MIT

crypto-reviewer

07

BostonOrange/claude-code-framework

Agent Claude Code

Reviews changed code for cryptographic failures — weak hashes, password storage, RNG misuse, encryption mode/IV mistakes, JWT pitfalls, TLS config, key derivation, constant-time comparison. Cites the crypto rule. Covers OWASP A02:2021.

not rated 3 3mo ago A 57 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Reviews diffs for material changes (package manager, test framework, build tool, directory layout, env vars, CI workflows, framework/ORM/auth provider swaps, breaking API changes) that landed without a corresponding CLAUDE.md / AGENTS.md / README update. Cites the docs-staleness rule. Read-only. Distinct from…

not rated 3 3mo ago A 99 tokens original MIT

dry-reviewer

09

BostonOrange/claude-code-framework

Agent Claude Code

Reviews changed code for true duplication — repeated knowledge, repeated logic, repeated structural patterns appearing 3+ times. Cites the dry rule. Distinct from code-smell-reviewer (other smells).

not rated 3 3mo ago A 46 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Build phase 3 specialist — adds input validation, error handling, edge-case handling, and defensive code to the happy-path implementation. Tightly bound to the error-handling, auth-security, and data-protection rules. Constrained by all relevant .claude/rules/.

not rated 3 3mo ago A 66 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Self-improvement applier — reads .claude/state/improve-proposal.md, re-validates against the /setup-owned skip-list, applies improvements (CLAUDE.md placeholder fills, rule pattern updates, settings tweaks), writes audit log to .claude/state/improve-applied.md. Refuses to apply items in the skip-list. Paired with…

not rated 3 3mo ago A 97 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Self-improvement detector — scans the project, identifies improvements to CLAUDE.md placeholders, .claude/rules patterns, settings, and agent configs. Read-only by tool restriction. Builds the /setup-owned skip-list before scanning so improvements respecting onboarding decisions are filtered out at proposal time.…

not rated 3 3mo ago B 86 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Reviews changed frontend code for component composition, state management, hook discipline, data flow, render performance, module boundaries, and SSR/hydration concerns. Cites the frontend-architecture rule. Distinct from ui-ux-reviewer (visual/a11y/design system).

not rated 3 3mo ago A 62 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Build phase 2 specialist — fills in the core successful flow for stubs created by scaffold-implementer. Implements the "everything works" version. Defers error handling, edge cases, and validation to the edge-case-implementer phase. Constrained by all relevant .claude/rules/.

not rated 3 3mo ago A 67 tokens original MIT

impact-analyzer

15

BostonOrange/claude-code-framework

Agent Claude Code

On-demand precise impact analysis for a symbol or file. Greps for callers, reads them, classifies the cascade (direct/indirect/test-only), and writes a structured report at .claude/state/impact- .md. Used by /impact and callable by review/refactor agents before suggesting changes.

not rated 3 3mo ago A 68 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Reviews changed code for structured logging discipline, log levels, metrics coverage, tracing propagation, audit logs, alerting, and correlation. Cites the observability rule. Covers OWASP A09:2021.

not rated 3 3mo ago A 48 tokens original MIT

planner-coordinator

17

BostonOrange/claude-code-framework

Agent Claude Code

Orchestrates planning specialists (requirements-clarifier, scope-decomposer, risk-assessor, test-strategy-planner, plus architect/api-designer/database-architect when relevant) and synthesizes their outputs into a single implementation plan.

not rated 3 3mo ago A 50 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

First-time onboarding applier — reads .claude/state/setup-proposal.md (with user-confirmed values), validates the apply allowlist, snapshots existing files, then applies placeholder substitutions to CLAUDE.md, .claude/rules/, .claude/skills/, settings, and .gitignore. Refuses to run if ## Confirmed by user is empty.…

not rated 3 3mo ago B 100 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

First-time onboarding detector — inventories the repo (greenfield vs brownfield), runs 17-layer stack detection with tradeoff-explained options + recommended defaults, writes .claude/state/setup-proposal.md. Read-only by tool restriction. Paired with project-setup-applier and orchestrated by /setup. Distinct from…

not rated 3 3mo ago B 99 tokens original MIT

purity-reviewer

20

BostonOrange/claude-code-framework

Agent Claude Code

Reviews changed code for impure functions, hidden side effects, query/command separation violations, input mutation, hidden state reads, and SRP violations at function and class level. Cites the purity rule.

not rated 3 3mo ago A 48 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Build phase 6 specialist (final pass before review) — actively applies code-quality rules to the just-implemented code: simplifies, extracts, dedupes, reduces complexity. Tightly bound to code-smells, dry, purity, complexity rules. Goal is that the review-coordinator finds little to flag.

not rated 3 3mo ago A 75 tokens original MIT

BostonOrange/claude-code-framework

Agent Claude Code

Hunts ambiguity in a story or task description before planning starts. Surfaces open questions, undefined terms, missing acceptance criteria, conflicting requirements, and assumed-but-unstated constraints.

not rated 3 3mo ago A 40 tokens original MIT

review-coordinator

23

BostonOrange/claude-code-framework

Agent Claude Code

Synthesizes findings from parallel reviewer agents into one consolidated report — dedupes, filters false positives, applies cross-iteration state, classifies the diff into a risk tier, and decides which sub-agents to spawn.

not rated 3 3mo ago A 48 tokens original MIT

risk-assessor

24

BostonOrange/claude-code-framework

Agent Claude Code

Identifies rollback paths, blast radius, breaking-change risk, data-migration danger, and operational risk for a planned change. Output feeds into the plan so risky steps get extra scrutiny.

not rated 3 3mo ago A 40 tokens original MIT

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: