nextc-ecc

Plugin nextc-ecc from marketplace nextc-claude in nextc/nextc-claude. Commands read from the repo's manifest — 5 days ago.

Skills (21)

• adversarial-review

  Require independent review approval before high-stakes output ships, breaking the single-reviewer blind-spot problem. Use when about to ship output where a missed defect is costly.

• agent-introspection-debugging

  Self-debug AI agent failures and produce an introspection report. Use when an agent stalls, loops, returns garbage, fails silently, or drifts off-task.

• agent-self-evaluation

  Self-rate your own output on evidence-backed axes before handing it back, catching omissions and overconfidence. Use when you have completed a non-trivial deliverable.

• aside

  Answer a quick side question mid-task without losing context, then resume work automatically. Use when the user interjects with a short question that should not derail the current task.

• canary-watch

  Verify a deployed URL against a baseline after a release. Use when you have just deployed, after merging a risky PR, or to confirm a fix in the live environment.

• code-tour

  Generate a persona-targeted CodeTour `.tour` walkthrough anchored to real, verified file and line locations. Use when the user wants a reusable guided walkthrough artifact rather than a one-off chat answer.

• codebase-onboarding

  Analyze an unfamiliar codebase and produce a structured onboarding guide. Use when you first open a repo, when joining a new team, or when bootstrapping Claude Code in an unfamiliar codebase.

• context-budget

  Audit Claude Code context-window consumption and surface a prioritized token-savings list. Use when the context bar is high, a session feels slow or expensive, or before installing more skills or agents.

• council

  Get structured multi-perspective disagreement on an ambiguous decision, tradeoff, or go/no-go call. Use when multiple valid paths exist and you need a second opinion.

• learn-eval

  Extract reusable patterns from the current session and file them in the right scope. Use when a session that surfaced a pattern worth keeping.

• opensource-pipeline

  Prepare a private project for safe public open-source release. Use when preparing a private repo for public release.

• production-audit

  Local-evidence production-readiness audit that scores ship/block risk without sending repo data anywhere. Use when you need a pre-deploy, post-merge, or pre-launch risk pass.

• resume-session

  Load the most recent saved session and orient fully before resuming work. Use when starting a fresh session that should pick up prior work.

• safety-guard

  Prevent destructive operations on production systems and during autonomous agent runs. Use when working on production, running agents in full-auto, or doing migrations and deploys.

• save-session

  Capture current session state to a dated file so the next session can pick up exactly where this one ended. Use when ending a work session or before hitting context limits.

• search-first

  Research existing tools, libraries, and patterns before writing custom code. Use when about to build common infrastructure such as auth, payments, file upload, or caching.

• strategic-compact

  Suggest a manual `/compact` at logical task boundaries instead of waiting for arbitrary auto-compaction. Use when context approaches limits or when switching between unrelated tasks.

• team-builder

  Compose and dispatch an ad-hoc team of specialist agents on demand. Use when a task needs two or more specialists working concurrently.

• token-budget-advisor

  Let the user choose response depth before answering. Use when the user wants to control response length or answer depth.

• verification-loop

  Confirm the build is green before handoff, commit, or PR. Use when code edits are done and before commit or PR, or as a quality gate.

• workspace-surface-audit

  Read-only audit of a workspace's repo, MCP servers, plugins, and env surfaces with install recommendations. Use when setting up Claude Code in a new repo or taking inventory of capabilities.

Subagents (15)

• a11y-architect

  Accessibility architect specializing in WCAG 2.2 AA for web and native UIs. Use PROACTIVELY when designing UI components, establishing a design system, or auditing UI for inclusive access (screen readers, keyboard/switch, target size, contrast).

• architect

  Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.

• build-error-resolver

  Build and compile error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.

• code-architect

  Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints with concrete files, interfaces, data flow, and build order. Use PROACTIVELY when planning a feature that spans multiple files or must fit existing codebase patterns.

• code-explorer

  Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, and documenting dependencies to inform new development. Use PROACTIVELY when understanding unfamiliar code before modifying it, or when tracing how a feature works end-to-end.

• code-reviewer

  Expert code review specialist. Reviews code for quality, security, and maintainability. Use PROACTIVELY immediately after writing or modifying code, before commit, or when the user says "review this", "check my changes", or "is this ready to ship".

• code-simplifier

  Simplifies and refines code for clarity, consistency, and maintainability while preserving behavior. Focus on recently modified code unless instructed otherwise. Use PROACTIVELY after implementation and before code review to reduce noise.

• opensource-forker

  Fork any project for open-sourcing — copies files, strips secrets and credentials (20+ patterns), replaces internal references with placeholders, generates .env.example, and cleans git history. Spawned by /opensource-pipeline skill — not invoked directly.

• opensource-packager

  Generate complete open-source packaging for a sanitized project — produces CLAUDE.md, setup.sh, README.md, LICENSE, CONTRIBUTING.md, and GitHub issue templates. Makes any repo immediately usable with Claude Code. Spawned by /opensource-pipeline skill — not invoked directly.

• opensource-sanitizer

  Verify an open-source fork is fully sanitized before release. Scans for leaked secrets, PII, internal references, and dangerous files using 20+ regex patterns. Generates a PASS/FAIL/PASS-WITH-WARNINGS report. Use PROACTIVELY before any public release.

• planner

  Expert planning specialist for complex features and refactoring. Use PROACTIVELY when the work spans multiple files, requires architectural decisions, or when the user says "plan this", "what's the approach", "how should we tackle this", "before I start coding", or "break this down".

• refactor-cleaner

  Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools to identify dead code and safely removes it.

• security-reviewer

  Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.

• silent-failure-hunter

  Review code for silent failures, swallowed errors, bad fallbacks, and missing error propagation. Use PROACTIVELY after writing error-handling code or when debugging "why didn't this error surface" / "works on my machine" bugs.

• spec-miner

  Extracts behavioral specs (Requirements + Invariants with stable IDs) from an existing codebase. Use PROACTIVELY when onboarding a brownfield project to spec-driven work, or when the user says "extract specs", "mine the behavior", "what does this code actually guarantee", or "document the existing c

Hooks (8)

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/block-no-verify.js"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/config-protection.js"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/fact-force-guard.js"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pre-commit-quality.js"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/suggest-compact.js"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/tool-awareness.js"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/loop-scope-guard.js"

• Stop

  node "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/verify-before-claim-scan.js"

Similar plugins