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/evasion_integrate)<a href="https://agentmods.dev/commands/seaof0/dsh-redteam-model/evasion_integrate"><img src="https://agentmods.dev/badge/commands/seaof0/dsh-redteam-model/evasion_integrate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/seaof0/dsh-redteam-model/evasion_integrate"><img src="https://agentmods.dev/badge/commands/seaof0/dsh-redteam-model/evasion_integrate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00517 |
| Opus 5 | $0.00000 | $0.00259 |
| Sonnet 5 | $0.00000 | $0.00103 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
evasion_integrate 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 9d 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 evasion_integrate — 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.
What it actually says
Evasion Integrate Command
Launch the evasion-agent to add evasion techniques to an existing loader.
Usage
/evasion_integrate /path/to/loader.c # Auto-select techniques
/evasion_integrate /path/to/loader.c --type api_obfuscation # Specific type
/evasion_integrate /path/to/loader.c --type string_obfuscation,anti_analysis
/evasion_integrate /path/to/loader.c --complexity simple # Filter by complexity
/evasion_integrate /path/to/loader.c --technique T001,T003 # Specific IDs
What This Command Does
- Reads user-provided loader source code
- Queries evasion techniques from knowledge base
- Analyzes compatibility with the loader
- Integrates selected techniques into the code
- Compiles modified loader
- Reports all changes made
Evasion Types
| Type | Description | Complexity |
|---|---|---|
| api_obfuscation | API hashing, PEB walking | medium |
| string_obfuscation | XOR encryption, stack strings | simple |
| memory_evasion | Permission flipping (RW→RX) | simple |
| execution_evasion | Direct/indirect syscall | complex |
| anti_analysis | Anti-debug, anti-VM | medium |
| amsi_etw_bypass | AMSI/ETW patching | medium |
| unhooking | NTDLL unhooking | complex |
Output
- Modified source:
output/evasion_<id>.c - Compiled executable:
output/evasion_<id>.exe - Changes summary:
- Techniques applied
- APIs modified
- Detection risk assessment
Security
- ONLY modify user-provided code
- NEVER run generated executables
- Compilation success is sufficient
Agent
Spawns evasion-agent subagent for technique integration.
See evasion_integrate skill for detailed patterns.
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.
- 9d ago First seen · 61 lines · 0 tokens per session scan A e4e5f0dae148
evasion_integrate is a command published in the GitHub repository SeaOf0/dsh-redteam-model (325 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 517 tokens. A static security scan graded it A with 0 findings. It is 100% identical to evasion_integrate, 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.