ccf
01Plugin Claude Code
Claude Context First workflow plugin marketplace.
Plugin Claude Code
Claude Context First workflow plugin marketplace.
Instructions file
Instructions for naniiluja/ccf, covering ccf — claude context first (plugin source), what this is, repo layout, core invariants (read before editing) and rules (imported — keep this file < 200 lines).
Plugin Claude Code
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.
MCP server Claude CodeCodexCursor +2
MCP server "microsoft-learn", hosted remotely at learn.microsoft.com, as configured in naniiluja/ccf.
MCP server Claude CodeCodexCursor +2
Context7's hosted MCP server: up-to-date library documentation and code examples on demand. Remote server at mcp.context7.com.
Agent
Fetches current best practices for given technologies/patterns from Context7 and Microsoft Learn and returns a concise, CITED recommendation. Read-only, and it drafts no spec and writes no files. Used by /ccf:init and /ccf:plan to ground design decisions.
Agent
Read-only explorer that analyzes ONE slice of an existing codebase and returns a structured report of what exists. Proposes no solutions and writes no files. Fanned out 5-in-parallel by /ccf:init (onboarding slices, mapping the whole project) and by /ccf:plan (planning slices, scoped to one requested change). Use this…
Agent
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.
Agent
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.
Agent
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), including a premortem / prospective-failure lens anchored to past iterations. Read-only…
Agent
Drafts CLAUDE.md and .claude/rules/.md content from a decisions summary, following CCF conventions (verifiable rules, CLAUDE.md under 200 lines, @import). Returns proposed file content; the main thread is the one that writes. Used by /ccf:init and /ccf:updatespec.
Command
Verify an implementation against the CCF spec — conformance, coding conventions, SOLID/OOP, and BE↔FE cross-check. Read-only review.
Command
Execute the entire todo/in-progress backlog sequentially via ccf-implementer, then batch-verify (review + code-review in parallel, simplify, re-gate, updatespec).
Command
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.
Command
Bootstrap a new project or onboard an existing one into the CCF workflow — generate CLAUDE.md + .claude specs + an initial sequential plan.
Command
Create a strictly sequential (waterfall) implementation plan, grounded in best practices. Requires plan mode.
Command
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".
Hook
Runs before the agent uses a tool for ExitPlanMode tool calls, executing plan-review-gate.mjs via node. From naniiluja/ccf.
Hook
Runs when you submit a prompt, before the agent sees it, executing plan-mode-guard.mjs and context-guard.mjs via node (2 commands). From naniiluja/ccf.
Hook
Runs when a session starts on startup, clear and compact, executing session-start.mjs via node. From naniiluja/ccf.
Hook
Runs when the agent finishes a response, executing updatespec-nudge.mjs and auto-verify.mjs via node (2 commands). From naniiluja/ccf.
Hook
Runs when a subagent starts for Explore tool calls, executing agent-rules-inject.mjs and explore-guide-inject.mjs via node (2 commands). From naniiluja/ccf.
Hook
Runs when a subagent finishes for ccf-implementer tool calls, executing implementer-verify-gate.mjs via node. From naniiluja/ccf.
Skill Claude CodeCodex
Internal requirements-interview engine for the CCF commands plan, fix and init. Invoked only by those commands through the Skill tool with a mode argument (plan / fix / init); it interrogates the user one question at a time, exploring the code to self-answer first, and returns a summary of the decisions. Not a…