Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By naniiluja
Claude Context First — a context-first, spec-driven, strictly sequential development workflow. Keeps CLAUDE.md/.claude specs continuously fresh and grounds every design decision in best practices fetched from Context7 and Microsoft Learn.
npx claudepluginhub naniiluja/ccf --plugin ccfVerify an implementation against the CCF spec — conformance, coding conventions, SOLID/OOP, and BE↔FE cross-check. Read-only review.
Systematic, step-by-step debugging — no rushing. Reproduce the bug, trace logs + DB step by step, judge the root cause, write a failing test, then fix minimally.
Bootstrap a new project or onboard an existing one into the CCF workflow — generate CLAUDE.md + .claude specs + an initial sequential plan.
Create a strictly sequential (waterfall) implementation plan, grounded in best practices. Requires plan mode.
Refresh the CCF spec (.claude/rules + CLAUDE.md) AND system memory with what was learned this session, so future sessions start fresh and repeat fewer mistakes. Also records new tools with "when to use".
Fetches current best practices for given technologies/patterns from Context7 and Microsoft Learn and returns a concise, CITED recommendation. Used by /ccf-init and /ccf-plan to ground design decisions.
Read-only explorer that analyzes ONE slice of an existing codebase and returns a structured report. Used by /ccf-init (5 in parallel) to onboard existing projects into CCF.
Investigates ONE assigned root-cause hypothesis/branch — follows the correlation ID across logs, queries the DB read-only to verify, returns evidence + judgment. Does NOT fix code. Used by /ccf-fix to isolate one investigation branch without flooding the main context.
Implements EXACTLY ONE task from .claude/plan/task-NNN-*.md — reads the relevant spec + rules, writes a failing test first then code to meet the acceptance criteria, uses MCP to look up DB schema/docs when needed. Does no other task, no out-of-scope refactor.
Fresh-context reviewer that checks an implementation against the CCF spec — conformance, conventions, SOLID/OOP, spec drift, BE↔FE consistency — OR critiques a PLAN as a staff engineer (vertical slicing, gates, predecessors). Read-only, returns findings with file:line, does NOT fix code or rewrite the plan.
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Harness-native ECC plugin for engineering teams - 64 agents, 261 skills, 84 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
English · Tiếng Việt · 简体中文
A workflow plugin for Claude Code that enforces a context-first, spec-driven, strictly sequential way of working:
CLAUDE.md + .claude/, kept continuously fresh so every session starts with fresh context.be/ and fe/ each with a nested spec./plugin marketplace add naniiluja/ccf
/plugin install ccf@ccf
npx @naniiluja/ccf
(runs claude plugin marketplace add + install for you)
claude plugin marketplace add D:/projects/ccf
claude plugin install ccf@ccf
After installing, open Claude Code in your project folder and run /ccf:ccf-init.
| Command | What it does |
|---|---|
/ccf:ccf-init | Bootstrap a new project (interview → generate CLAUDE.md + .claude + plan) or onboard an existing one (5 analyzer agents). |
/ccf:ccf-plan | Create a sequential plan for one feature. Requires plan mode (Shift+Tab). After planning, execute each task with an agent. |
/ccf:ccf-check | Verify the implementation against the spec (conformance, conventions, SOLID/OOP, BE↔FE cross-check). |
/ccf:ccf-fix | Disciplined debugging: reproduce → trace logs/DB step by step → root cause → failing test → fix. |
/ccf:ccf-updatespec | Update the spec and system memory with this session's lessons (incl. new tools with "when to use"). |
Typical flow: ccf-init → (plan mode) ccf-plan → implement → ccf-check → /code-review → ccf-updatespec.
The plugin bundles 2 MCP servers (plugin scope, auto started/stopped by Claude Code):
https://learn.microsoft.com/api/mcp (remote HTTP, no auth required).https://mcp.context7.com/mcp (remote HTTP, works out of the box without a key).Context7 rate limit: the plugin runs Context7 without an API key (free rate limit). If you hit a rate limit, get a free key at context7.com/dashboard, set the
CONTEXT7_API_KEYenv var, and restart Claude Code.
/ccf:ccf-updatespec records lessons in two places with different purposes:
CLAUDE.md + .claude/rules/) — loaded as a user message, lower weight. Holds project rules: conventions, architecture, tech-stack, tooling.~/.claude/projects/<path>/memory/) — loaded into the system prompt, not down-weighted, so Claude follows it more strongly. Holds anti-mistake feedback + user preferences across sessions → helps Claude repeat fewer mistakes.Principle: no duplication. A rule in CLAUDE.md that keeps getting forgotten → write a feedback memory that reinforces it (with the "why"), rather than copying its content.
A proactive /compact <hint> beats letting auto-compact fire (when context has "rotted" the model is at its least sharp). After you compact, CCF's SessionStart hook (matcher compact) auto re-loads the in-progress task from .claude/plan/PLAN.md, restoring the right work context so you don't have to paste it back.
.mjs run directly with node — no build step, no dependency, Windows-clean.See plugins/ccf/ for details. Requires Node ≥ 18 for the hooks.
MIT