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.
git clone --depth 1 https://github.com/SeaOf0/dsh-redteam-modelWrote 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.
[](https://agentmods.dev/commands/seaof0/dsh-redteam-model/tools_evasion)<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>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.
| Model | Per session | Once 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 |
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.
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.
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
- Read README and documentation files
- Analyze source code structure
- Identify programming language and build system
- Determine tool purpose and use cases
- Create tool profile at
rules/{tool_name}/tool_profile.md
Phase 2: Open Source Detection (if applicable)
- Check if the tool is open source
- Extract keywords (name, author, features)
- Search GitHub for tool-specific detection rules
- Save found rules to
rules/{tool_name}/yara/,rules/{tool_name}/sigma/, etc.
Phase 3: Behavior Analysis
- 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
- Extract behavioral signatures
- Search for behavior-based detection rules
- Save found rules
Phase 4: Rule Collection
- Organize all found rules
- Create rule inventory at
rules/{tool_name}/rule_inventory.md - Categorize by type (YARA, Sigma, Network, etc.)
Phase 5: Per-Rule Analysis
For EACH detection rule found:
- Parse all patterns (strings, hex, regex)
- Identify pattern sources in the tool code
- Develop evasion strategies (prioritize compiler flags)
- Create analysis file at
rules/{tool_name}/rule_analysis/{rule_name}.md
Phase 6: Source Modification
CRITICAL: Directly modify source files using Edit tool.
- FIRST: Try build configuration changes (compiler flags)
- SECOND: Apply source code modifications if needed
- Create tasks for each modification
- Verify each change
Modification priority:
- Compiler flags (lowest effort, highest impact)
- Build configuration
- String obfuscation
- API obfuscation
- Function rename
- Behavior change (last resort)
Phase 7: Verification & Summary
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.
- 8d ago First seen · 126 lines · 0 tokens per session scan A 03c49cddb08c
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.
Other commands, from other repositories
riskreview
The user invoked the /riskreview facade command from the risk-review-pipeline pack.
hello-stranger
Say hello stranger.
approval
The user invoked the /approval facade command from the approval-node-pipeline pack.
aw
The user invoked the /approval-web facade command from the approval-node-pipeline pack.
kf
A customer-support command for TeamClaw, a software product. It sends a user's question to a support workflow that can search help information, examine logs, and create defect reports.
workflow-dispatcher
The user invoked the /workflow-dispatcher facade command from the workflow-dispatcher pack.