By TheSylvester
Agentic coding toolkit: sub-agent orchestration, prompt synthesis, and browser automation for Claude Code
Synthesize implementation prompts for a fresh agent - auto-decomposes if task is too large
Multi-vendor adversarial review — parallel agents, skeptical verification, iterative consensus
Synthesize a complete implementation spec for a pair-programming session with a new coding agent to collaboratively build the discussed task
Reflect on conversation + codebase to ensure prompts capture everything before execution
Code review for uncommitted changes, staged changes, specific files, or a PR
Visual UI testing and verification via browser automation. Use when testing user flows, checking styling/formatting, or investigating UI issues in the browser.
Analyze Claude Code transcripts (.jsonl). Use for searching history, extracting patterns, comparing sessions.
Web UI cloning specialist. Use when you need to create pixel-perfect HTML/CSS/JS reproductions of websites by visual observation. Analyzes target UIs via browser automation, extracts styling, generates code, and iteratively refines until matching. Handles sidebars, cards, lists, code blocks, diffs, and common UI patterns.
Holistic design critic that engages with a super-agent-driven walkthrough. Expects a walkthrough prompt file path as input. Spawns the walkthrough as a super-agent, then critiques the design at each milestone — catching under-engineering, over-abstraction, missing edge cases, and cross-cutting issues that the implementing agent couldn't see while building piece by piece.
Build a phased prompt chain with orchestration file from a monolithic implementation prompt
Extract and save browser screenshots from session transcripts
Wrapper around codex CLI for non-interactive runs (prompt via args/file/stdin) with resume support. Outputs session_id for conversation continuation.
Multi-agent debate orchestrator. Use when you want multiple AI perspectives on a question, plan review, or architectural decision. Runs parallel agent panels with a Chair synthesizing responses.
Wrapper around cursor-agent CLI for non-interactive runs (prompt via args/file/stdin) with resume support.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Stop losing context when Claude hits limits. Hand off tasks to fresh agents with full specs automatically synthesized from your conversation.
You: "Build the auth system we discussed"
/handoff-prompt-to super-agent
→ Synthesizes a complete implementation spec from conversation context
→ Spawns a fresh agent with the spec
→ Agent executes with full context, no token debt
/plugin marketplace add TheSylvester/agentic-coding-tools
/plugin install agentic-coding-tools
Or install individual skills:
/plugin install super-agent
/plugin install chrome-screenshot
When context gets heavy, synthesize a prompt and hand off to a fresh agent:
/handoff-prompt-to super-agent — Full spec, fresh execution/pair-prompt-to super-agent — Collaborative pair-programming mode/reflect — Validate your prompts before executionFor large tasks that exceed single-agent capacity:
/build-prompt-chain — Decompose into phases with orchestration file/super-agentbrowser-qa agent — Visual UI testing and verificationui-clone agent — Pixel-perfect HTML/CSS reproductions/chrome-screenshot — Extract screenshots from session transcripts| Skill | Description |
|---|---|
super-agent | SDK-based Claude agent with full Task tool access |
cursor-agent | Cursor IDE agent wrapper with resume support |
gemini-agent | Gemini CLI wrapper with resume support |
git-worktree | Create worktrees with auto-symlinked local files (.env*, .ai-*) |
build-prompt-chain | Transform monolithic prompts into phased chains |
chrome-screenshot | Extract browser screenshots from transcripts |
read-transcript | Token-efficient transcript reading |
| Command | Description |
|---|---|
/handoff-prompt-to | Synthesize implementation prompts for fresh agents |
/pair-prompt-to | Create specs for pair-programming sessions |
/walkthrough-prompt-to | Generate design walkthrough prompts |
/reflect | Validate prompts against conversation + codebase |
| Agent | Description |
|---|---|
browser-qa | Visual UI testing via browser automation |
ui-clone | Pixel-perfect website reproduction |
Same prompt synthesis tools for other AI assistants:
| Platform | Setup |
|---|---|
| Cursor IDE | cp -r .cursor/commands/* ~/.cursor/commands/ |
| Gemini CLI | cp -r .agent/workflows/* ~/.agent/workflows/ |
This repo is both a Claude Code config directory AND a marketplace source.
~/.claude/ # Can be this repo
├── .claude-plugin/
│ ├── plugin.json # Plugin metadata
│ └── marketplace.json # Lists all installable plugins
├── skills/ # Individual skills
│ └── <skill-name>/
│ ├── SKILL.md # Documentation + frontmatter
│ ├── .claude-plugin/plugin.json # Makes it individually installable
│ └── scripts/<skill-name> # Executable (if any)
├── commands/ # Slash commands (.md files)
├── agents/ # Subagent definitions (.md files)
└── plugins/ # GITIGNORED - for installed plugins
└── marketplaces/
└── agentic-coding-tools → ../.. (symlink to root)
# One-time symlink setup
mkdir -p plugins/marketplaces
ln -s ../.. plugins/marketplaces/agentic-coding-tools
skills/<name>/SKILL.md with YAML frontmatterskills/<name>/.claude-plugin/plugin.jsonskills/<name>/scripts/<name> (if needed).claude-plugin/marketplace.jsonclaude plugin validate .This repo IS the marketplace.
claude plugin validate .mkdir -p plugins/marketplaces && ln -s ../.. plugins/marketplaces/agentic-coding-tools/pluginMIT
npx claudepluginhub thesylvester/agentic-coding-tools --plugin read-transcriptPersonal Claude Code / Codex skills — spec-driven development, agent teams, browser automation, productivity, and setup helpers. Install with `npx skills add devstefancho/claude-plugins`.
Claude Code の SubAgent(agents/*.md)を正しく定義するためのベストプラクティスガイド。 YAML frontmatter、ツール選択、3-Phase 構造、コンテキスト受け渡し、アンチパターンを網羅。 Use when: agents/*.md を書く、SubAgent 定義を改善する、エージェントの動作が想定外、 コンテキストが渡らない、ツール選択に迷う。 Triggers: "subagent", "agent definition", "agents/*.md", "エージェント定義", "サブエージェント", "3-Phase", "context passing", "コンテキスト渡し", "tool selection", "ツール選択", "subagent_type", "bypassPermissions"
HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, unified QA gates, safety guards, and notifications.
Workflow skills and agents: code-walk-thru, log-work, make-issue-spec skills; ui-tester agent for browser-based UI validation
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Agents for UI/UX design, accessibility, and user experience optimization