agentrigs
+ submit rig
~ / rigs / Encod3d-Sec / TORCH

Encod3d-Sec/TORCH

Karpathy LLM based claude harness for PenetrationTesting / Bugbounty using obsidian

↗ GitHub ★ 268 mit updated 2mo ago project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~8.3k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Encod3d-Sec/TORCH/skills ./rig-torch/skills

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.

$ npx degit Encod3d-Sec/TORCH/skills/claude-md-improver .claude/skills/claude-md-improver
$ npx degit Encod3d-Sec/TORCH/skills/disclosure .claude/skills/disclosure
$ npx degit Encod3d-Sec/TORCH/skills/research .claude/skills/research
$ npx degit Encod3d-Sec/TORCH/skills/wiki .claude/skills/wiki

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (4)

claude-md-improverdisclosureresearchwiki

Similar rigs

SynaLinks/synalinks
Keras based framework for neuro-symbolic LM systems
★ 462 project Claude CodeCodex 1 skills 14d ago
Minimalist 840 tok ·
plasma-ai/wiki
Indexed knowledge bases with command-line tools for agents.
★ 101 project Claude CodeCodex 1 skills 17d ago
Pragmatist 5.7k tok ·
ProjectMakersDE/ai-agent-wiki
Template for a wiki that AI coding agents read before they work: routers for Claude Code, Codex, Cursor, Copilot and Gemini, maintained in Obsidian.
★ 1 project Claude CodeCodexGemini CLI 1 skills 2 hooks 11d ago
Minimalist 290 tok ·
nvk/llm-wiki
LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.
★ 1,379 project Claude CodeCodex 3 skills 7d ago
Pragmatist 15.1k tok ·
copied ✓