107 ready-made Claude agents — code review, copywriting, analytics, support, growth, legal. Drop them into Claude Code and watch the right one auto-route in under 5 seconds.
Premium agents
Categories
Free updates
Pay, own forever
What you can actually do
See it work
Each example is the actual format you get when Claude routes to the named subagent in Claude Code.
You
Review the diff on this branch for security issues before I merge.
Agent output
🔴 Blocking — fix before merge 1. app/api/auth.ts:42 — JWT secret hardcoded in source. Move to env. 2. app/api/upload.ts:15 — SSRF: fetch URL is user-controlled, no allowlist. 3. lib/db.ts:88 — SQL built via string concat. Parameterize. 🟡 Should fix 1. middleware.ts:23 — rate limit only by IP, trivially bypassed by VPN.
You
/api/checkout returns 500 only on Fridays around 6pm IST. Logs show nothing useful.
Agent output
## Hypotheses (likeliest first) 1. Weekly cron clobbers DB connections — test: align cron schedule against 500 timestamps. 2. Friday traffic spike exhausts pool — test: pool metrics + latency p99. 3. Time-zone bug treating Fri evening as off-hours — test: grep for Date comparisons. ## Next observation Pull the last 4 Fridays' 500s with timestamps. Cluster in 5 min → cron. Spread → pool.
You
Write 3 Meta ad variants for the agents pack. Indian audience.
Agent output
Hook 1 — price flex Spent ₹40k on ChatGPT Plus this year? 107 ready-made Claude agents for ₹499. One-time. Hook 2 — workflow Drop one file. Claude becomes your QA, copywriter, analyst, support team. Hook 3 — contrarian Stop writing prompts. Drop subagent files instead. Claude auto-routes in 5 seconds.
Inside the agents pack
Engineering, content, marketing, business, data, productivity, legal, India-context, personal — 9 categories.
5-minute install guide plus deep reference for customization, chaining, and troubleshooting.
Working TypeScript project built on the Anthropic SDK. Run it, fork it, ship it.
v1.1 adds 30+ more agents plus 2 more SDK starters — free for existing buyers.
A tiny fraction of what you get:
Under the hood
Every agent is a single markdown file. YAML frontmatter tells Claude when to use it; the body is the system prompt. Plain text — read it, edit it, version-control it.
---
name: code-reviewer
description: Use when reviewing a diff, pull request, or commit
before merge. Focuses on correctness and footguns.
tools: Read, Grep, Glob, Bash
---
You are a senior code reviewer. Your job is to catch the things a
careless review would miss, while ignoring things that don't matter.
## What to look for, in order
1. Correctness. Does the code do what the diff claims?
2. Security. Anything touching user input, auth, secrets, or APIs.
3. Concurrency & state. Race conditions, stale caches, retries.name
Stable identifier. Call explicitly or let Claude auto-route by description.
description
How Claude decides whether to use this agent. Sharper = more reliable routing.
tools
Optional subset of Claude Code tools. Security-auditor can be read-only by design.
system prompt body
Plain markdown — identity, rules, process. Edit freely for your codebase or voice.
5-minute install
No accounts. No API keys. If you have Claude Code, you're 60 seconds from your first agent.
User-scoped install — agents available across every project.
unzip agents-bundle.zip && cp -r agents-bundle/subagents/* ~/.claude/agents/Agents live inside one repo, version-controlled with the code.
mkdir -p .claude/agents
cp -r agents-bundle/subagents/* .claude/agents/Claude auto-routes by reading every agent's description field.
# Auto-route
> "Review the last commit for security issues."
# Explicit
> "Use bug-hunter on the 500 on /api/x."Each agent is plain markdown. Sharpen the system prompt with your codebase context.
code ~/.claude/agents/code-reviewer.mdChain them together
Claude orchestrates hand-offs between agents. Output from one becomes context for the next.
Find root cause, lock in a regression test, then review the diff before merge — one prompt.
Positioning gap → 3 Meta variants → tone consistency review across all copy.
Honest TAM/SAM/SOM → discovery interview script → launch motion from real learnings.
9 categories
Curated agents that earn their keep — opinionated, focused, ready to fire.
15+
12+
11+
13+
12+
14+
10+
5+
14+
Compatibility
Native fit. Drop into ~/.claude/agents/ — Claude auto-routes by description. Primary target.
Copy agent body into Project custom instructions. Same prompts, manual selection.
Project .claude/agents/ folder — whole team gets agents. Subagent routing works out of the box.
TypeScript starter (customer-research-agent) on the SDK. Fork for autonomous scheduled agents.
Pricing
Made for Claude Opus 4.8 · Mythos Level Intelligence
Launch Pricing — ₹499
Launch pricing — rises to ₹999 on July 1, 2026
107 specialized agents with auto-routing
What you get
₹2,499
₹499
One-time payment · Lifetime access · No subscription
All 2,000+ skills, 107 agents, 50 Projects, the 40-lesson Claude Studio course, AND the AI Influencer Creator workbook + 20 videos. Every guide. Every starter. Lifetime updates.
₹799
₹399
Pay with
FAQ
Native fit is Claude Code — drop into ~/.claude/agents/ for auto-routing. Copy agent body text into Claude.ai Projects for the same prompts without auto-routing.
User-scoped (~/.claude/agents/) works across all projects. Project-scoped (.claude/agents/ in repo) shares agents via git with your team. Project agents override user agents with the same name.
Yes. Describe the full workflow in one prompt — Claude orchestrates hand-offs. The pack includes example chains for debugging, launches, and research.
No. AdsxGrowth is an independent product. We are not affiliated with Anthropic or Claude.
After checkout you receive an email with secure download links. You can also log in with the same email to re-download anytime.
Yes. One payment includes lifetime updates for the packs you purchase.
107 agents covering every role you wish you could afford. ₹499 once. Made for Claude Opus — Mythos-level intelligence inside.
Need help? Email hi@adsxgrowth.com — 24×7 support
Agents Pack
₹499₹2,499