claude

ccc

Composable Code Codex: composition-first, pure-function-friendly code quality enforcement for TypeScript, JavaScript, Python, Go, and Rust. Orchestrates 21 check sub-skills covering boundaries, purity, immutability, typed errors, types, naming, tests, security, observability, and strategic DDD.

0 on GitHubby mikecubedv4.1.0MITupdated 3 months agodeveloper-tools
/

Plugin ccc from marketplace agent-orchestration in mikecubed/agent-orchestration. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (22)

  • a11y-check

    Accessibility pattern enforcement for TypeScript (TSX) and JavaScript (JSX). Detects missing alt text, non-semantic HTML, absent ARIA roles, keyboard-inaccessible interactive elements, and click-only event handlers. Wired into the conductor's review operation.

  • arch-check

    Enforces architectural boundary rules: BOUND-1 (boundary direction — core imports nothing from shell or infrastructure), BOUND-2 (stable ports — no concrete infrastructure types in core public signatures), BOUND-3 (composition root owns wiring — no hidden construction in core), BOUND-4 (no circular

  • conductor

    Core orchestrator for Composable Code Codex enforcement. Auto-invoked when writing, reviewing, refactoring, or testing code in TypeScript, Python, Go, Rust, or JavaScript. Detects language, routes to targeted check sub-skills, enforces the test gate on write operations, and runs a Boy Scout check at

  • context-check

    Strategic DDD enforcement: CTXT-1 (shared models leaking across unrelated bounded contexts), CTXT-2 (vague generic names in domain — cross-references NAME-UL), CTXT-3 (external API models leaking into core without an anti-corruption layer). Loaded by the conductor for review and new-service operatio

  • dead-check

    Enforces dead code elimination rules (DEAD-1 through DEAD-5). Loaded by the conductor for review, refactor, and cleanup operations. Detects commented-out code, unused exports, orphaned files, unlinked TODOs, and stub/placeholder functions. References scripts/lint_dead_code.py for export and orphan d

  • dep-check

    Enforces dependency health rules (DEP-1 through DEP-5). Loaded by the conductor for dependency update operations and CI full-check runs. Detects known vulnerabilities, version lag, unused dependencies, misclassified dev/prod dependencies, and unpinned production versions. Invokes scripts/dep_audit.s

  • docs-check

    Documentation coverage enforcement for TypeScript, JavaScript, Python, Go, and Rust. Detects missing JSDoc/docstrings on exported symbols, misleading or stale inline comments, and absent README files in new packages. Does not overlap with dead-check (commented-out code). Wired into the conductor's r

  • gate-check

    Enforces the test gate on write and test operations. Two rules: TEST-PINNED (no new code is shippable without a test that exercises it) and TEST-RED-FIRST (sessions must record at least one red→green transition for new code, proving the test is not vacuous). Replaces the old strict-ordering TDD-1..9

  • i18n-check

    Internationalization enforcement for TypeScript, JavaScript, and Python. Detects hardcoded user-visible strings, locale-unaware date/number/currency formatting, and missing translation keys. Wired into the conductor's review and write operations.

  • iac-check

    Enforces IaC security rules (IAC-1 through IAC-5). Loaded by the conductor for security audits and review operations on infrastructure-as-code files. Detects public storage buckets, containers running as root, missing encryption-at-rest, wildcard IAM policies, and exposed ports in security groups. S

  • immutability-check

    Enforces immutability rules: IMMUT-1 (no parameter mutation across function boundaries in core — produce new values rather than mutate inputs), IMMUT-2 (no shared mutable state across concurrency boundaries), IMMUT-3 (no field reassignment after construction in core types). Loaded by the conductor f

  • naming-check

    Enforces naming convention rules (NAME-1 through NAME-7, plus NAME-UL). Loaded by the conductor for write and review operations. Detects meaningless names, incorrect boolean prefixes, misleading names, abbreviations, naming inconsistencies, and (for files in `core/`) generic technical suffixes that

  • obs-check

    Enforces observability rules (OBS-1 through OBS-5). Loaded by the conductor for review, incident response, and new service scaffolding. Detects empty catch blocks, unstructured logging, missing endpoint tracing, absent health checks, and vague error messages. Activated by: "incident", "on call", "de

  • perf-check

    Enforces performance rules (PERF-1 through PERF-3). Loaded by the conductor for review operations. Detects N+1 query patterns, unbounded loops over large collections, and missing pagination on list endpoints using static analysis.

  • purity-check

    Enforces functional-core purity rules: PURE-1 (no side effects in core/ modules — no I/O, no clock, no RNG, no logging), PURE-2 (no ambient/global state reads in core), PURE-3 (mock-required-to-test signal — if a function needs a mock to test, it isn't pure and belongs in shell). Loaded by the condu

  • resilience-check

    Static resilience-pattern analysis. Detects missing retry/backoff, absent circuit breakers, unbounded timeouts, and missing deadline propagation in TypeScript, JavaScript, Python, Go, and Rust. Wired into the conductor's review and write operations.

  • result-check

    Enforces typed-error rules: RESULT-1 (domain failures should return typed errors / Result<T,E> rather than raw exceptions — BLOCK in Rust and TypeScript where the pattern is idiomatic, WARN in Python and JavaScript where exceptions are conventional), RESULT-2 (avoid null/None for not-found — use Opt

  • sec-check

    Enforces security rules (SEC-1 through SEC-7). Loaded by the conductor for security audits, PR/code reviews, incident response, and new service scaffolding. Detects hardcoded secrets, insecure credential handling, XSS vectors, SQL injection, gitignore gaps, stale credentials, and CORS misconfigurati

  • session-check

    Session hygiene enforcement. Detects stale or absent session state, exceeded failed-hypothesis budgets, and missing codebase briefs before non-trivial implementation tasks. Wired into the conductor's write and review operations. Renamed from ctx-check in v4.0 to free the "context" namespace for the

  • size-check

    Enforces code size and complexity rules (SIZE-1 through SIZE-6). Loaded by the conductor for write, review, and refactor operations. Detects oversized functions, files, deep nesting, long parameter lists, flag arguments, and God classes. Size thresholds are language-agnostic — no language reference

  • test-check

    Enforces test quality rules (TEST-1 through TEST-9, plus TEST-BEHAVIOR, TEST-NO-MOCK-FOR-PURE, TEST-VACUOUS). Loaded by the conductor for review and test operations. Detects weak assertions, insufficient coverage, missing property tests, slow unit tests, I/O in unit tests, missing boundary condition

  • type-check

    Enforces type-safety rules (TYPE-1 through TYPE-6) plus type-driven design rules (TYPED-1, TYPED-2). Loaded by the conductor for write and review operations. Blocks use of escape-hatch types, unsafe assertions, and missing exhaustive pattern matching. Warns on primitive obsession (same primitive as

Slash commands (1)

  • /ccc:codex

    Run the Composable Code Codex conductor against the current codebase or a specified path. Detects language and operation type, dispatches only the required check sub-skills, enforces the TDD gate, checks waivers, and produces a structured violation report. Use /codex to audit code quality across Typ

Subagents (1)

  • ccc

    Composable Code Codex enforcement agent. Auto-invoked when writing, reviewing, refactoring, or testing code in TypeScript, JavaScript, Python, Go, or Rust. Detects language and operation type, enforces TDD gate on write operations, and routes to targeted sub-skills (tdd, arch, type, naming, size, de

Hooks (12)

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-sec-write.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-arch-write.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-purity-write.sh

  • PreToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-sec-bash.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-quality.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-coverage-delta.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-obs-write.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-immut-write.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-result-write.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-verification.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-dep.sh

  • PostToolUse

    ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/hook-validation-record.sh

View source on GitHub

More from mikecubed/agent-orchestration

All 3 plugins →

flow

claude

Idea-to-done conductor, planning, delivery, codebase mapping, architecture review, brainstorm ideation, parallel implementation, systematic debugging, incident RCA, e2e test generation, review resolution, PR readiness, diff review, worktree lifecycle, swarm orchestration, contract generation, PR publication, release, knowledge capture, knowledge refresh, and SDD specification skills.

21 skills · 7 agents

0

patterns

claude

Design pattern advisor, evaluator, refactoring planner, and interactive teacher grounded in canonical software architecture books. Includes Fowler's PEAA, Gang of Four, and Evans' DDD pattern catalogs.

13 skills

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review

1 command · 3 agents

anthropics/claude-code 155,476

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

AI-powered codebase understanding — analyze, visualize, and explain any project

9 skills · 10 agents · hooks

Egonex-AI/Understand-Anything 92,410

Maintain ccc?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins3 plugins