Skip to main content
Glama

⚑ AGENT SUPERPOWERS

Transform Your AI Coding Agent into a Battle-Tested Principal Staff Engineer

Stop AI hallucinations, broken production commits, and 100k-token context bloat.
*A disciplined, deterministic 7-stage autonomous engineering framework natively compatible with Claude Code, Cursor, Google Antigravity, Windsurf, Codex, and Model Context Protocol (MCP).*

Release Skills Count Tests MCP Protocol License: MIT

πŸ›‘ 1. Deterministic Repro

πŸ“¦ 2. Ephemeral Sandbox

🟒 3. Minimal Surgical Patch

βš”οΈ 4. Red-Team Fuzzing

πŸš€ 5. Production Gate

RED Test Required

Worktree Isolation

GREEN Verification

11 Attack Payloads

Verified Merge

Zero code edits allowed until bug replicates

Primary branch protected from corrupting edits

Minimal patch turns failing repro green

Null-bytes, SQLi & overflow injection

100% regression suite verified

⭐ Found this useful? Star this repository to empower the open-source autonomous engineering movement!


⚑ Quick Start (Instant 1-Command Setup)

Install the complete 36-skill suite and autonomous Python engines in seconds:

πŸͺŸ Windows (Native PowerShell)

irm https://raw.githubusercontent.com/GabrieleDattile/agent-superpowers/main/install.ps1 | iex

🐧 macOS / Linux (Native Bash)

curl -fsSL https://raw.githubusercontent.com/GabrieleDattile/agent-superpowers/main/install.sh | bash

πŸ”Œ Universal MCP Server (Claude Desktop, Cursor, Zed, Antigravity)

Add to your claude_desktop_config.json or .cursor/mcp.json:

{
  "mcpServers": {
    "agent-superpowers": {
      "command": "python",
      "args": ["mcp/server.py"],
      "cwd": "/path/to/agent-superpowers"
    }
  }
}

πŸ“¦ Node.js / NPX

npx github:GabrieleDattile/agent-superpowers list

Related MCP server: local-skills-mcp

⚑ The Difference: Default AI vs. Agent Superpowers

Without guardrails, even state-of-the-art LLMs behave like chaotic junior developers: they jump straight into editing files, hallucinate non-existent APIs, break existing tests, and push unverified changes.

The Chaos of Default AI ❌

With Agent Superpowers Protocol 🟒

Hallucinates bug fixes: Edits production code based on guesswork

Ghost Runner: Strictly forbidden from editing source code until a minimal failing test reproduces the defect (RED βž” GREEN)

Corrupts your workspace: Makes sweeping multi-file edits directly on your active working branch

Git Worktree Sandbox: Runs all experiments in ephemeral, isolated git worktrees; primary branch remains 100% clean

Generates fragile edge-cases: Writes happy-path code vulnerable to boundary crashes and exploits

Adversarial Duelist: Automated pre-commit red-team fuzzer injects null-bytes, SQLi payloads, and zero-divisions

Produces generic AI slop: Default purple gradients, formulaic 3-card grids, Inter font, unanchored blur blobs

Hallmark: Anti-AI-slop design engine with 24 distinct material themes and automated sloplint auditor

Blows token budgets: Dumps full source files into context, hitting rate limits and burning money

Token Squeezer: Shrinks prompt context by 50–70% using AST extraction without losing architectural semantics

Breaks frontend layouts: Generates UI code that looks fine on desktop but breaks on mobile viewports

Frontend Sentinel: WCAG 2.1 accessibility and responsive breakpoint auditor with visual HTML reports

Session amnesia: Forgets past architectural decisions and conventions every time the CLI restarts

Memory Nexus: Append-only local decision ledger (.superpowers/decisions.jsonl) persists context cross-session

Locked into closed ecosystems: Inability to interface with proprietary tools and APIs

Blackbox Cloner & API Synthesizer: Clean-room tool replication and automatic cURL-to-SDK synthesis


🎬 Live Deep-Dives: See How the Skills Work in Action

1. πŸ” Ghost Runner: Strict TDD Bug Reproduction

Rule: An agent is forbidden from modifying production files until it writes an isolated test that replicates the bug and fails (RED).

# Run Ghost Runner reproduction gate
python cli/superpowers.py run ghost-runner reproduce --test "python -m unittest tests/test_reproduce.py"
=== πŸ‘» Ghost Runner: TDD Reproduction Protocol ===
Test Command: python -m unittest tests/test_reproduce.py
Expected Outcome: FAILURE (RED)

Running test under isolated subshell...
----------------------------------------------------------------------
ZeroDivisionError: division by zero in calculate_discount()
Ran 1 test in 0.002s
FAILED (failures=1)

βœ” SUCCESS: Defect reproduced deterministically (Exit Code: 1).
  Agent is now AUTHORIZED to apply minimal surgical patch in worktree.

2. πŸ›‘οΈ Adversarial Duelist: Pre-Commit Red-Team Fuzzing

Rule: Before any commit or PR is approved, the agent attacks the proposed function with 11 boundary payloads to catch unhandled crashes.

# Fuzz an authentication or payment function
python cli/superpowers.py run duelist --target services/auth.py --func authenticate_user
=== βš”οΈ Adversarial Duelist: Red-Team Fuzzer ===
Target: services/auth.py :: authenticate_user()
Testing 11 adversarial injection vectors...

  βœ” [01/11] Null-Byte Poisoning ('admin\x00')      βž” Handled (ValueError)
  βœ” [02/11] SQL Injection (' OR '1'='1' --)       βž” Handled (Safe Query)
  βœ” [03/11] Memory Bounding ('A' * 100,000)        βž” Handled (LengthGuard)
  βœ” [04/11] Zero Divisor (divisor=0)               βž” Handled (ZeroGuard)
  βœ” [05/11] Float NaN / Infinity (val=float('nan')) βž” Handled (TypeError)
  βœ” [06/11] Boundary Integer (2^63 - 1)            βž” Handled (OverflowSafe)
  ...
βœ” 11/11 Attack Vectors Defended. Pre-commit authorization granted.

3. 🎨 Hallmark & Sloplint: The Anti-AI-Slop Design Engine

Rule: Prevent LLMs from defaulting to generic AI tropes (purple gradients, predictable 3-card grids, floating blur balls).

# Audit a landing page or UI component for machine-made design tells
python cli/superpowers.py run sloplint src/components/Hero.tsx
=================================================================
🎨 Hallmark Sloplint: Autonomous Anti-AI-Slop Auditor
=================================================================
Scanned: src/components/Hero.tsx

Found 3 aesthetic tells:
  πŸ”΄ [SLOP-001] Generic AI Purple Gradient (Line 14)
     Match: 'bg-gradient-to-r from-purple-500 to-indigo-600'
     Fix:   Adopt a deliberate palette from Hallmark themes (e.g. Cobalt, Atelier, Furrow).

  πŸ”΄ [SLOP-002] Unanchored Floating Blur Orb (Line 8)
     Match: 'rounded-full blur-3xl bg-purple-500/30'
     Fix:   Replace decorative blobs with real photography, technical diagrams, or clean space.

  🟑 [SLOP-003] AI Buzzword Copy (Line 18)
     Match: 'Supercharge your productivity with AI'
     Fix:   Write concrete, specific value propositions with real numbers and features.

Overall Slop Index: 60 / 100 [FAIL (HIGH SLOP CONTENT)]
Guidance: Apply curated theme tokens from references/themes.json

4. ⚑ Token Squeezer: AST-Based Prompt Compressor

Rule: Shrink massive codebases by 50–70% before injecting them into prompt context windows, preserving signatures and docstrings.

# Compress a 500-line service down to its architectural essence
python cli/superpowers.py run squeezer services/payment.py --mode interface
# === ORIGINAL (1,420 Tokens) ===              # === SQUEEZED (-68% Tokens) ===
class PaymentGateway:                           class PaymentGateway:
    """Handles Stripe and PayPal charges."""        """Handles Stripe and PayPal charges."""
    def __init__(self, key: str):                   def __init__(self, key: str): ...
        self.key = key                              def charge(self, amount: float,
        self._init_vault()                                     currency: str = "USD") -> bool: ...
        self._connect_webhook()                     def refund(self, txn_id: str) -> bool: ...
    def charge(self, amount: float, ...) -> bool:
        # [80 lines of internal logic]
        ...

5. πŸ—ΊοΈ Arch Archaeologist & Graphify: Codebase Cartography

Rule: Map live module dependencies, trace call trees, and detect dead zombie functions across the entire repository.

flowchart TD
    subgraph Core ["πŸ“¦ Core Services"]
        AUTH["auth.py<br/><i>authenticate_user()</i>"]
        GATEWAY["gateway.py<br/><i>process_payment()</i>"]
    end
    subgraph Storage ["πŸ’Ύ Storage Layer"]
        DB["database.py<br/><i>query_records()</i>"]
        CACHE["cache.py<br/><i>get_session()</i>"]
    end
    subgraph DeadCode ["⚠️ Dead Zombie Code (Isolated)"]
        LEGACY["legacy_v1_api.py<br/><i>[0 references detected]</i>"]
    end

    AUTH --> DB
    AUTH --> CACHE
    GATEWAY --> DB
    style LEGACY stroke:#ef4444,stroke-dasharray: 5 5,color:#ef4444

πŸ”„ The 7-Stage Autonomous Lifecycle

Every coding task executes through an auditable, deterministic state machine:

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”       β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”       β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚ 1. BRAINSTORM   β”‚ ────> β”‚ 2. WORKTREE     β”‚ ────> β”‚ 3. MAP &        β”‚
β”‚ Requirements    β”‚       β”‚ Sandbox Branch  β”‚       β”‚ Compress (AST)  β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜       β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜       β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                                              β”‚
                                                              β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”       β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”       β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚ 6. RED-TEAM     β”‚ <──── β”‚ 5. SURGICAL     β”‚ <──── β”‚ 4. TDD PROOF    β”‚
β”‚ Fuzzing & Audit β”‚       β”‚ Green Patch     β”‚       β”‚ Fail First (RED)β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜       β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜       β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
        β”‚
        β–Ό
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚ 7. SAFE MERGE   β”‚ ────> Verified Production-Ready Artifact
β”‚ & PR Gate       β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

πŸ“¦ Complete Autonomous Superpowers Suite (36 Skills)

Superpower

Category

Primary Capability

using-superpowers

🧠 Orchestration

Master bootstrap meta-skill; enforces the 7-stage engineering lifecycle

feature-brainstormer

πŸ’‘ Workflow

Socratic requirements refiner; asks 3 clarifying questions before writing code

git-worktree-sandbox

πŸ“¦ Workflow

Ephemeral git worktree isolation; zero risk of corrupting your active workspace

Superpower

Category

Primary Capability

ghost-runner

πŸ” Debugging

Zero-assumption bug reproducer; enforces strict RED βž” GREEN TDD cycle

testsprite-verify

πŸ§ͺ Testing

Closed-loop automated regression and user flow verification

testsprite-ci

πŸ§ͺ Testing

CI pipeline test automation and test suite orchestration

Superpower

Category

Primary Capability

adversarial-duelist

πŸ›‘οΈ Security

Pre-commit red-team fuzzer; injects malicious edge-case payloads

blackbox-cloner

πŸ•΅οΈ Reverse Engineering

Clean-room tool replicator; deconstructs proprietary software into open-source scaffolds

api-synthesizer

πŸ”Œ Integration

Network-to-SDK generator; converts cURL traffic into typed Python client SDKs

Superpower

Category

Primary Capability

arch-archaeologist

πŸ—ΊοΈ Architecture

Codebase cartographer; traces dependency graphs and isolates dead zombie functions

graphify

πŸ—ΊοΈ Architecture

AST-driven persistent knowledge graph of codebases, schemas, and docs without vector DB

hindsight-architect

πŸ—ΊοΈ Architecture

Memory architect for application design patterns and decisions

memory-nexus

πŸ’Ύ Memory

Cross-session architecture ledger; eliminates agent amnesia between restarts

hindsight-memory

πŸ’Ύ Memory

Adaptive long-term project memory and automatic session synthesis

Superpower

Category

Primary Capability

token-squeezer

⚑ Optimization

AST-based context compressor; cuts LLM prompt token costs by 50–70%

caveman

⚑ Optimization

Terse smart-caveman voice; eliminates fluff while preserving all technical facts

caveman-compress

⚑ Optimization

Extreme token compression for memory files and long context

prompt-optimizer

⚑ Optimization

Systematic prompt evaluation, few-shot generation, and constraint tuning

Superpower

Category

Primary Capability

hallmark

🎨 Frontend

Anti-AI-slop design engine; overrides generic purple gradients with 24 material themes & sloplint

frontend-sentinel

🎨 Frontend

Production UI/UX auditor; checks a11y, mobile viewports & generates visual HTML reports

figma-designer

🎨 Frontend

Token-driven Figma design specs, components, auto-layout, and design systems

landing-page-design

🎨 Frontend

High-converting landing page blueprints, copywriting, and visual structure

review-frontend-production

🎨 Frontend

Production frontend inspection, compliance checks, and handover verification

Superpower

Category

Primary Capability

scrapling

πŸ•ΈοΈ Scraping

Adaptive web scraping framework with anti-bot bypass and stealth browser sessions

firecrawl-build

πŸ•ΈοΈ Scraping

In-app Firecrawl integration for live web data, extraction, and search

firecrawl-scrape

πŸ•ΈοΈ Scraping

Single-page extraction into structured markdown

firecrawl-search

πŸ•ΈοΈ Scraping

Agent web discovery before extraction

firecrawl-interact

πŸ•ΈοΈ Scraping

Post-scrape browser actions, form filling, and pagination

firecrawl-onboard

πŸ•ΈοΈ Scraping

Firecrawl SDK credentials, auth flows, and project onboarding

agent-reach

πŸ•ΈοΈ Scraping

Zero-API reading and search across public web sources, video transcripts, and developer platforms

Superpower

Category

Primary Capability

ponytail

πŸ“ Workflow

YAGNI principal engineer mindset; smallest change that fully solves the task

ponytail-audit

πŸ“ Workflow

Whole-repo bloat and unnecessary dependency audit

ponytail-debt

πŸ“ Workflow

Technical debt and shortcut tracking ledger

ponytail-review

πŸ“ Workflow

Pull request quality and anti-overengineering reviewer

caveman-commit

πŸ“ Workflow

Intent-only Conventional Commits generator

video-shotcraft

🎬 Multimedia

Programmatic Remotion cinematic product video synthesis


πŸ› οΈ Universal Platform Support

Agent Superpowers is completely runtime-agnostic. Drop it into your existing workflow with zero configuration:


πŸ“Š Mission Control Dashboard

Agent Superpowers ships with an interactive local web dashboard with zero external dependencies. Visualize your skills, architecture dependency graphs, and test telemetry in real time:

python cli/superpowers.py dashboard

πŸš€ CLI Commands & Validation

Agent Superpowers includes a built-in verification suite:

# List all 36 registered superpowers
python cli/superpowers.py list

# Run system health check across all engines
python cli/superpowers.py status

# Validate specification compliance
python cli/superpowers.py validate

# Run the automated unit test suite
python -m unittest tests/test_skills.py

🀝 Contributing

Contributions are warmly welcomed!

  1. Check our formal Agent Skill Specification.

  2. Propose new skills via the New Skill Template.

  3. Ensure CI verification passes (python cli/superpowers.py validate).


πŸ‘€ Author

Gabriele D'Attile


πŸ“„ License

This project is licensed under the MIT License.

Available Tools

9 tools
adversarial_duelistB

Offensive red-team fuzzer. Attacks a Python function with null-bytes, zero-divisions, overflow payloads, and SQLi vectors.

Inputs: target_file (required), function_name (required).

api_synthesizerC

Reverse-engineers raw cURL network traffic into a fully typed Python client SDK.

Inputs: curl_command (required), client_name.

arch_archaeologistC

Scans codebase AST to map module dependency graphs and detect uncalled zombie/dead functions.

Inputs: dir_path (required).

blackbox_clonerC

Clean-room reverse engineering engine. Deconstructs proprietary tools and SaaS widgets into independent open-source specs and scaffolds.

Inputs: action (required), tool_name (required), category.

frontend_sentinelA

Audits React, Vue, and HTML templates for accessibility defects, mobile viewport breaks, and hydration hazards.

Inputs: path (required), html_report.

ghost_runnerB

Zero-assumption TDD bug reproducer. Requires test to FAIL before patching, and PASS after patching.

Inputs: mode (required), test_cmd (required).

git_worktree_sandboxB

Creates, merges, or discards isolated git worktrees so agent experiments never corrupt main workspace.

Inputs: action (required), task_name.

hallmark_sloplintA

Anti-AI-slop design auditor. Scans HTML, JSX, TSX, Svelte, and Vue files for generic AI tells (purple gradients, predictable 3-card grids, unanchored blur orbs, corporate buzzwords).

Inputs: target, fail_under.

token_squeezerC

AST-based context compressor. Shrinks Python source files by 50-70% by extracting structural interfaces and docstrings.

Inputs: file_path (required), mode.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 9 tools

    Disambiguation4/5

    Most tools target clearly distinct capabilities: API synthesis, TDD bug reproduction, fuzzing, context compression, dependency archaeology, git sandboxing, frontend accessibility auditing, blackbox cloning, and AI-design linting. There is some conceptual adjacency between api_synthesizer and blackbox_cloner (both reverse engineering) and between frontend_sentinel and hallmark_sloplint (both frontend/design audits), but their descriptions make the boundaries usable.

    Naming Consistency4/5

    All names use consistent snake_case and follow a descriptive agent-persona pattern rather than a verb_noun action pattern. The style is predictable overall, with only minor variation such as the three-word git_worktree_sandbox and a mix of modifier_noun forms.

    Tool Count5/5

    Nine tools is well within the appropriate range for a specialized agent-superpowers toolkit. Each tool represents a distinct capability and none appear redundant or purely filler.

    Completeness3/5

    The set covers several advanced coding-agent workflows, but as a broad 'superpowers' toolkit it has notable gaps: no general code search/navigation, refactoring, documentation generation, dependency management, or performance profiling. These omissions are not fatal because the tools are specialized add-ons, but they mean the surface is not a complete lifecycle.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers