Cc Plugin Market
MCP server: Cc Plugin Market
Installation
npx cc-plugin-marketAsk AI about Cc Plugin Market
Powered by Claude Β· Grounded in docs
I know everything about Cc Plugin Market. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
CC Plugin Market
Two complementary Claude Code plugins for Spec-Driven Development: reverse-engineer existing code into structured specs + queryable knowledge graph (Spectra), and orchestrate new feature development through 8-mode autonomous workflows (Spec Driver).
Table of Contents
- What's inside
- Project Milestones
- Quick Start
- Spectra
- Spec Driver
- Plugin Installation
- Documentation
- Contributing Β· License
What's inside
| Plugin | One-liner |
|---|---|
| Spectra | Code β Spec + Knowledge Graph + MCP query tools (AI assistants get persistent architecture memory) |
| Spec Driver | Idea β Spec β Plan β Code (autonomous SDD orchestrator with 8 modes + project-level workflow overrides) |
ββββββββββββββββββββββββββββ ββββββββββββββββββββββββββββββββ
β Spectra β β Spec Driver β
β (Reverse Engineer) β β (Forward Orchestrator) β
β β β β
β Code β Spec + Graph β β Idea β Spec β Plan β Code β
β + MCP for AI assistants β β + Per-project overrides β
ββββββββββββββββββββββββββββ ββββββββββββββββββββββββββββββββ
Project Milestones
| Milestone | Status | Highlights | Docs |
|---|---|---|---|
| M-100 Spectra Evolution | β Delivered | reverse-spec β Spectra rebrand Β· panoramic Phase 1οΌε€θ―θ¨η΄’εΌγθ·¨ε δΎθ΅γLLM θ―δΉε’εΌΊγε€ζ ΌεΌθΎεΊοΌ | blueprint |
| M-101 Phase 2 β Reading Platform | β Delivered | Graph schema v2.0 + Hyperedges Β· LLM cost transparency Β· SpecStore + sourceKind Β· TODO/Open Questions extraction Β· Natural language Q&A + interactive graph.html Β· Default model upgrade to Sonnet 4.6 / Opus 4.7 1M | blueprint Β· postmortem |
| M-102 / M-103 Phase 3 | π‘ In Progress | Python AST function-level graph (v4.1) Β· E2E fixture infrastructure Β· large-project baseline Β· LLM concurrency optimizer | proposal |
Quick Start
# 1. Install Spectra CLI globally
npm install -g spectra-cli
# 2. Add the marketplace to Claude Code
claude plugin marketplace add connor-git-yaml/cc-plugin-market
# 3. Install both plugins (user-scope, available across all projects)
claude plugin install spectra@cc-plugin-market --scope user
claude plugin install spec-driver@cc-plugin-market --scope user
# 4. In any project, generate a Spec + Knowledge Graph
cd your-project/
spectra batch --mode reading --html # ~2-5 min for typical project
# 5. Use Spec Driver for new features (in Claude Code)
/spec-driver:spec-driver-feature Add OAuth2 login flow
After step 4, AI coding assistants (Claude Code, Cursor, Codex with MCP) can query your codebase architecture via 6 MCP tools β see How AI Coding Assistants Use Spectra below.
Spectra
A hybrid AST + LLM pipeline that reverse-engineers source code into structured Spec documents and builds a persistent knowledge graph of architecture relationships. Multi-language (TS/JS/Python/Go/Java), multi-format export (Markdown / Obsidian Vault / interactive graph.html), MCP-queryable.
Spectra Highlights
- π 9-section module specs β AST-extracted intent / interface / data / dependencies / quality / lifecycle / etc. (TS/JS interface 100% AST-extracted)
- π Knowledge graph schema v2.0 β
references/conceptually_related_to/rationale_foredges + multi-node hyperedges - π 6 MCP query tools β natural language graph queries that AI assistants can call directly
- π Interactive
graph.htmlβ D3-force visualization with hyperedge convex hulls (self-contained, no server) - π° LLM cost transparency β
--dry-runcost preview +--budget Nenforcement +tokenUsagein every spec frontmatter - β‘ Lightweight modes β
--mode reading(skip product docs) /--mode code-only(skip all LLM, AST-only) - π§ Technical debt extraction β TODO/FIXME/HACK code comments + design-doc Open Questions
- π Continuous sync β
spectra watch(file watcher) orspectra install(post-commit hook) - π Multi-language β TS/JS (ts-morph) + Python (AST + tree-sitter) + Go/Java/Rust (tree-sitter)
- π― Honest uncertainty β
[inferred]/[unclear]labels; raw source never sent directly to LLM - π Read-only safety β writes limited to
specs/,_meta/,drift-logs/
π€ How AI Coding Assistants Use Spectra
The big idea: Spectra builds a persistent architecture knowledge graph once, then any MCP-aware AI assistant queries it on demand β no re-reading the entire codebase every session.
βββββββββββββββββββββββ Step 1: Build once
β Your codebase β βββββββββββββββββββ
β (any language) β $ spectra batch --html --hyperedges
ββββββββββββ¬βββββββββββ β
β
βΌ
βββββββββββββββββββββββ
β specs/ β Persistent artifacts:
β βββ modules/ β β’ 9-section module specs
β βββ project/ β β’ technical-debt.md
β βββ _meta/ β β’ graph.json (schema v2.0)
β βββ graph.jsonβ β’ graph.html (D3 interactive)
β βββ graph.htmlβ β’ GRAPH_REPORT.md (communities + god nodes)
ββββββββββββ¬βββββββββββ
β Step 2: AI queries via MCP
β βββββββββββββββββββββββββ
βΌ
ββββββββββββββββββββββββββββββββββββββββββββββββββ
β Claude Code / Cursor / Codex / Aider / ... β
β β
β User: "Where is auth handled?" β
β β
β AI calls MCP graph_query("auth") β
β β β
β Returns: relevant module specs + dependencies β
β β β
β AI answers with cited specs + line numbers β
ββββββββββββββββββββββββββββββββββββββββββββββββββ
MCP query tools (6 + natural-language Q&A)
| Tool | Purpose | Example call |
|---|---|---|
graph_query | Keyword + BFS subgraph traversal | graph_query({ question: "auth module", budget: 30 }) |
graph_node | Single node details + neighbors | graph_node({ id: "src/auth/login.ts" }) or { keyword: "login" } |
graph_path | Shortest dependency path between two nodes | graph_path({ source: "cli/main.ts", target: "db/connection.ts" }) |
graph_community | All members of a detected community | graph_community({ communityId: "c-0" }) |
graph_god_nodes | Top-degree hub nodes (core abstractions) | graph_god_nodes({ topK: 10 }) |
graph_hyperedges | Multi-node participation patterns | graph_hyperedges({ filter: "ingestion" }) |
Plus the higher-level panoramic-query MCP tool with natural-language operation (Phase 2 F5):
panoramic-query({
operation: "natural-language",
question: "What calls storage directly? What's the shortest path from parser to processor?",
projectRoot: "."
})
// β Returns RAG-style answer with cited spec excerpts + line numbers + graph context
This is AI-for-AI architecture memory: the AI never has to re-read your codebase from scratch.
Why this matters
- Token economics β Querying a 50K-token graph instead of re-reading 500K LOC saves 90%+ tokens per session
- Cross-session memory β
_meta/graph.jsonpersists between Claude Code sessions; AI can ask "what changed since last time?" - Multi-IDE compatible β Same MCP server works for Claude Code, Cursor, Codex, Aider, OpenCode, etc.
- Hook-driven freshness β
spectra installregisters a post-commit hook that incrementally rebuilds the graph; AI always queries the latest
Trigger via auto-injection (PreToolUse hook)
When spectra install is active, Claude Code's PreToolUse hook automatically injects relevant architecture summary before the AI runs Grep / Glob searches β so the AI knows the answer is in specs/modules/auth.spec.md before fanning out to read 30 source files.
π Full details: docs/spectra-cli-reference.md
Spec Driver
Spec Driver is a Claude Code plugin that serves as an autonomous development orchestrator. Automates the full Spec-Driven Development lifecycle through 14 specialized sub-agents, 6 quality gates, 8 execution modes, and project-level workflow overrides.
Spec Driver Highlights
- πΌ 8 execution modes β
feature/implement/story/fix/refactor/resume/sync/doc - π¬ Parallel sub-agent dispatch β RESEARCH_GROUP, DESIGN_PREP_GROUP, VERIFY_GROUP run in parallel; auto-fallback to serial
- π¦ 6 quality gates β
GATE_RESEARCH/GATE_DESIGN/GATE_ANALYSIS/GATE_TASKS/GATE_IMPLEMENT_MID/GATE_VERIFY - π§ Per-project workflow overrides β
.specify/orchestration-overrides.yaml(like ESLint extends or Docker Compose override) - π― Multi-runtime model compat β Same configs work in Claude (Sonnet/Opus) and Codex (gpt-5.4 + thinking levels)
- π‘οΈ Quality reviews β
spec-review(compliance) +quality-review(architecture/readability) +verify(build/lint/test)
Mode selection (TL;DR)
| Scenario | Command |
|---|---|
| New feature, major requirement | /spec-driver:spec-driver-feature <desc> |
| Mature spec/plan, just implement | /spec-driver:spec-driver-implement |
| Iterative change | /spec-driver:spec-driver-story <desc> |
| Bug fix | /spec-driver:spec-driver-fix <desc> |
| Large refactor | /spec-driver:spec-driver-refactor <target> |
| Resume interrupted work | /spec-driver:spec-driver-resume |
| Aggregate product spec | /spec-driver:spec-driver-sync |
| Generate open-source docs | /spec-driver:spec-driver-doc |
π Full details: docs/spec-driver-modes.md β all phases, sub-agents, generated artifacts.
π Project-level workflow customization: docs/configuration.md#per-project-orchestration-overrides β override phases / gates / parallelism per project.
v4.0 Breaking Change: The 9 atomic commands (
/spec-driver.specifyetc.) have been removed. See migration guide.
Plugin Installation
Prerequisites
- Claude Code CLI installed and authenticated
- Node.js 20.x+
Note: Plugin Marketplace commands are Claude Code specific. For Codex, use the CLI + skill installation flow in the Codex section below.
Add the Marketplace
# GitHub shorthand (recommended)
claude plugin marketplace add connor-git-yaml/cc-plugin-market
# Or use the full HTTPS URL
claude plugin marketplace add https://github.com/connor-git-yaml/cc-plugin-market.git
Both forms register the marketplace under the name
cc-plugin-market(defined in.claude-plugin/marketplace.json), which the install commands below reference.
Install Plugins
# Install to current project (recommended β scoped to this project only)
claude plugin install spec-driver@cc-plugin-market --scope project
claude plugin install spectra@cc-plugin-market --scope project
# Or install for current user (available across all projects)
claude plugin install spec-driver@cc-plugin-market --scope user
claude plugin install spectra@cc-plugin-market --scope user
Update / Uninstall
# Refresh marketplace cache then reinstall to upgrade
claude plugin marketplace update cc-plugin-market
claude plugin install spec-driver@cc-plugin-market --scope <scope>
# Uninstall
claude plugin remove spec-driver --scope <scope>
claude plugin remove spectra --scope <scope>
Verify
claude plugin list # list installed plugins
/spec-driver:spec-driver-doc # test spec-driver
/spectra src/ # test spectra
Codex Support
π¦ Install for Codex (CLI + skills)
For Codex, install spectra CLI and register skills into .codex/skills:
# Install CLI
npm install -g spectra-cli
# Project-level Codex skills
spectra init --target codex
# Or global Codex skills
spectra init --global --target codex
# Install both Claude + Codex skills in one command
spectra init --global --target both
# Optional: control npm postinstall target with env var
SPECTRA_SKILL_TARGET=codex npm install -g spectra-cli # values: claude | codex | both
Spec Driver uses an independent Codex entrypoint (parallel to Spectra):
# Run from repository root
npm run codex:spec-driver:install # project-level
npm run codex:spec-driver:install:global # global
npm run codex:spec-driver:remove # remove
# Equivalent low-level scripts
bash plugins/spec-driver/scripts/codex-skills.sh install [--global]
Notes:
- Project mode installs to the current git repository root (or current directory when not in a git repo).
- Codex skills are generated from the current
spec-driver-*source skills with a small Codex runtime adapter block; reruninstallafter upgrading Spec Driver.
Documentation
- π Spectra CLI Reference β full command list, knowledge graph workflows, architecture pipeline diagram
- πΌ Spec Driver Modes β 8 modes detailed, sub-agents, generated artifacts, quality gates
- βοΈ Configuration β model presets (
spec-driver.config.yaml) + project-level orchestration overrides (.specify/orchestration-overrides.yaml) - ποΈ Repository Architecture β
src/layout, tech stack, testing, sync contracts - π€ Contributor Guide β full contribution flow
- π Migration Guides β v4.0 atomic skill removal, orchestration overrides
- π― Project Milestones β M-100 / M-101 / M-102+ blueprints and postmortems
Contributing
Bug reports and pull requests are welcome. Please open an issue first to discuss what you would like to change.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'feat: add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
See docs/contributor-guide.md for full guidelines including the repo:check validation requirements.
License
This project is licensed under the MIT License - see the LICENSE file for details.
