ishaankarnik11/phishforge-agentic
AI studio that turns a scenario brief into email-safe phishing-simulation templates, with GPT Image 2 image generation, mask editing and an asset library. For authorized security-awareness audits. Built with an agentic workflow: scoped Clau
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code
$ npx degit ishaankarnik11/phishforge-agentic/.claude ./rig-phishforge-agentic # inspect, then merge into .claude/ MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ curl -fsSL --create-dirs -o .claude/agents/ai-engineer.md https://raw.githubusercontent.com/ishaankarnik11/phishforge-agentic/main/.claude/agents/ai-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/backend-engineer.md https://raw.githubusercontent.com/ishaankarnik11/phishforge-agentic/main/.claude/agents/backend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/devops-engineer.md https://raw.githubusercontent.com/ishaankarnik11/phishforge-agentic/main/.claude/agents/devops-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/frontend-engineer.md https://raw.githubusercontent.com/ishaankarnik11/phishforge-agentic/main/.claude/agents/frontend-engineer.md $ curl -fsSL --create-dirs -o .claude/agents/qa-reviewer.md https://raw.githubusercontent.com/ishaankarnik11/phishforge-agentic/main/.claude/agents/qa-reviewer.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Subagents (5)
| ai-engineer | AI pipeline specialist. Use for all work in backend/app/ai/ including LangChain stages, prompt templates, Pydantic output schemas, Claude API integration, prompt caching, and structured output handlin |
| backend-engineer | Python 3.12 backend specialist. Use for any work in backend/app/ including FastAPI endpoints, SQLAlchemy models, Alembic migrations, Pydantic schemas, MJML subprocess rendering, and service-layer logi |
| devops-engineer | Infrastructure and deployment specialist. Use for docker-compose, Dockerfiles, CI pipelines, deployment scripts, and environment config. Invoked rarely — usually only during setup sprints or before re |
| frontend-engineer | React 18 + TypeScript + Vite frontend specialist. Use for any work in frontend/ including pages, components, GrapesJS editor integration, API clients, and styling. Does not touch backend code or Pytho |
| qa-reviewer | QA and code review specialist. Invoke at end of every story, before merging to main. Runs the full test suite, lints, type checks, verifies acceptance criteria from the PRD, and writes a review verdic |
Slash commands (3)
/merge-story/review-story/start-story
Similar rigs
bsrikumar855-dot/ClaudeCODE-Autonomous-skills
An autonomous AI development skill for Claude Code. Turn project goals into planned, implemented, tested, and reviewed software using specialist AI subagents.
Orchestrator 789 tok · · Q0
SaketMunda/claude-org-template
Drop this into any project and start engineering at AI speed. No setup ceremony. No re-explaining context every session.
Orchestrator 1.4k tok · · Q33
minanyang/10x-agent
A multi-agent workflow for shipping code: agents plan, build and review, and nothing lands without evidence a script can check.
Orchestrator 1.3k tok · · Q0
sagullapalli/claude-code-setup
Claude Code Setup for building fullstack applications
Orchestrator 1.5k tok · · Q13