tools_evasion

tools_evasion is a command for Claude Code from SeaOf0/dsh-redteam-model. It costs 0 tokens per session (870 once invoked), scanned A, a copy of tools_evasion, MIT.

A command for examining a penetration-testing tool, documenting how it works, finding public detection rules, and changing its source code to avoid detection.

In plain words
What is it for?
Use it to review a tool's documentation and code, identify its network, process, and file behavior, search GitHub for related detection rules, and save the results in a structured rules directory.
Why use it?
It turns an unfamiliar tool into a documented profile and organizes detection research by type, such as YARA or Sigma rules.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it to review a tool's documentation and code, identify its network, process, and file behavior, search GitHub for related detection rules, and save the results in a structured rules directory.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/seaof0/dsh-redteam-model/tools_evasion
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/SeaOf0/dsh-redteam-model

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tools_evasion

README.md
[![agentmods](https://agentmods.dev/badge/commands/seaof0/dsh-redteam-model/tools_evasion.svg)](https://agentmods.dev/commands/seaof0/dsh-redteam-model/tools_evasion)
Your own site
<a href="https://agentmods.dev/commands/seaof0/dsh-redteam-model/tools_evasion"><img src="https://agentmods.dev/badge/commands/seaof0/dsh-redteam-model/tools_evasion.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 870 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00870
Opus 5 $0.00000 $0.00435
Sonnet 5 $0.00000 $0.00174
Haiku 4.5 $0.00000 $0.00087

Measured 8d ago against content hash 03c49cddb08c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tools_evasion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to tools_evasion — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

modes/av-evasion/refs/subagents/commands/tools_evasion.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are tasked with analyzing a penetration testing tool and modifying its source code to evade detection.

Input

Tool Path: {{tool_path}}

Workflow

Follow these phases in order:

Phase 1: Tool Understanding

  1. Read README and documentation files
  2. Analyze source code structure
  3. Identify programming language and build system
  4. Determine tool purpose and use cases
  5. Create tool profile at rules/{tool_name}/tool_profile.md

Phase 2: Open Source Detection (if applicable)

  1. Check if the tool is open source
  2. Extract keywords (name, author, features)
  3. Search GitHub for tool-specific detection rules
  4. Save found rules to rules/{tool_name}/yara/, rules/{tool_name}/sigma/, etc.

Phase 3: Behavior Analysis

  1. Analyze source code for core behavior patterns:
    • Network behavior (HTTP headers, URLs, ports)
    • Process behavior (creation, injection)
    • File behavior (paths, operations)
    • API usage patterns
    • String constants
  2. Extract behavioral signatures
  3. Search for behavior-based detection rules
  4. Save found rules

Phase 4: Rule Collection

  1. Organize all found rules
  2. Create rule inventory at rules/{tool_name}/rule_inventory.md
  3. Categorize by type (YARA, Sigma, Network, etc.)

Phase 5: Per-Rule Analysis

For EACH detection rule found:

  1. Parse all patterns (strings, hex, regex)
  2. Identify pattern sources in the tool code
  3. Develop evasion strategies (prioritize compiler flags)
  4. Create analysis file at rules/{tool_name}/rule_analysis/{rule_name}.md

Phase 6: Source Modification

CRITICAL: Directly modify source files using Edit tool.

  1. FIRST: Try build configuration changes (compiler flags)
  2. SECOND: Apply source code modifications if needed
  3. Create tasks for each modification
  4. Verify each change

Modification priority:

  1. Compiler flags (lowest effort, highest impact)
  2. Build configuration
  3. String obfuscation
  4. API obfuscation
  5. Function rename
  6. Behavior change (last resort)

Phase 7: Verification & Summary

Read the full file on GitHub · 126 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 126 lines · 0 tokens per session scan A 03c49cddb08c

Subscribe to this mod's changes

tools_evasion is a command published in the GitHub repository SeaOf0/dsh-redteam-model (293 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 870 tokens. A static security scan graded it A with 0 findings. It is 100% identical to tools_evasion, differing in 0 lines, and is treated as a copy.