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.
npx agentmods add commands/seaof0/dsh-redteam-model/loader_generategit 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/loader_generate)<a href="https://agentmods.dev/commands/seaof0/dsh-redteam-model/loader_generate"><img src="https://agentmods.dev/badge/commands/seaof0/dsh-redteam-model/loader_generate.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 | $0.00000 | $0.00610 |
| Opus 5 | $0.00000 | $0.00305 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
loader_generate 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 5d 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 loader_generate — 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loader Generate Command
Launch the loadergen-agent to generate shellcode loaders from the knowledge base.
Usage
/loader_generate # Single random loader (uses samples/calc.bin)
/loader_generate 5 # Batch generate 5 loaders
/loader_generate --shellcode path/to/sc.bin # Use custom shellcode file
/loader_generate my.bin # Shorthand: use my.bin as shellcode
/loader_generate --executor callback # Specific executor
/loader_generate --allocator NtAllocateVirtualMemory
/loader_generate --complexity medium # Filter by complexity
/loader_generate --language rust # Rust loader
/loader_generate 3 --shellcode custom.bin # Batch with custom shellcode
What This Command Does
- Queries components from
loader_techniques.json - Checks duplicates in
scenarios.json - Generates code combining random/specified components
- Compiles with MinGW (C/C++) or Cargo (Rust)
- Records result in knowledge base
Components
| Category | Options |
|---|---|
| Storage | embedded, resource, remote_url, encrypted_resource |
| Allocator | VirtualAlloc, HeapCreate, NtAllocateVirtualMemory |
| Copier | memcpy, RtlMoveMemory, loop_copy |
| Executor | function_pointer, CreateThread, callback, APC, Fiber |
Output
- Generated source:
output/loader_<id>.c(or.cpp,.rs) - Compiled executable:
output/loader_<id>.exe - Knowledge base scenario ID
Shellcode File
| Option | Description |
|---|---|
--shellcode <path> |
Specify custom shellcode bin file |
| No flag | Uses default samples/calc.bin |
| Shorthand | <file.bin> treated as --shellcode <file.bin> |
Examples:
/loader_generate --shellcode ./payloads/custom.bin
/loader_generate 5 --shellcode my.bin
/loader_generate my.bin --executor callback
Security
- Default shellcode:
samples/calc.bin(for safe testing) - Custom shellcode: user-provided bin files allowed
- NEVER run generated executables
- Compilation success is sufficient
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.
- 5d ago First seen · 74 lines · 0 tokens per session scan A e6829b9336f1
loader_generate is a command published in the GitHub repository SeaOf0/dsh-redteam-model (183 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 610 tokens. A static security scan graded it A with 0 findings. It is 100% identical to loader_generate, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
ov
Show OpenViking memory plugin status — server, identity, last injection / recall, toggles.
manps
Inspect project health through mancode.
riskreview
The user invoked the /riskreview facade command from the risk-review-pipeline pack.
delegate
Delegate a task in the background / 在后台委派大型任务.
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.