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 skills add Njones17/AI-agent-master-cyber-skills-list --skill zeroize-auditgit clone --depth 1 https://github.com/Njones17/AI-agent-master-cyber-skills-listWrote 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/skills/njones17/ai-agent-master-cyber-skills-list/zeroize-audit)<a href="https://agentmods.dev/skills/njones17/ai-agent-master-cyber-skills-list/zeroize-audit"><img src="https://agentmods.dev/badge/skills/njones17/ai-agent-master-cyber-skills-list/zeroize-audit/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/skills/njones17/ai-agent-master-cyber-skills-list/zeroize-audit"><img src="https://agentmods.dev/badge/skills/njones17/ai-agent-master-cyber-skills-list/zeroize-audit.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 | $0.00057 | $0.05497 |
| Opus 5 | $0.00028 | $0.02749 |
| Sonnet 5 | $0.00011 | $0.01099 |
| Haiku 4.5 | $0.00006 | $0.00550 |
Grade A, and why
zeroize-audit 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
47 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- configs/c.yaml 456 B
- configs/default.yaml 3.9 KB
- configs/rust.yaml 3.2 KB
- prompts/report_template.md 6.5 KB
- prompts/system.md 7.9 KB
- prompts/task.md 4.3 KB
- references/compile-commands.md 9.9 KB
- references/detection-strategy.md 9.9 KB
- references/ir-analysis.md 11 KB
- references/mcp-analysis.md 9.0 KB
- references/poc-generation.md 21 KB
- references/rust-zeroization-patterns.md 35 KB
- schemas/input.json 3.1 KB
- schemas/output.json 5.9 KB
- tools/analyze_asm.sh 5.2 KB runs code
- tools/analyze_cfg.py 13 KB runs code
- tools/analyze_heap.sh 5.4 KB runs code
- tools/analyze_ir_semantic.py 15 KB runs code
- tools/diff_ir.sh 4.0 KB runs code
- tools/diff_rust_mir.sh 6.2 KB runs code
- tools/emit_asm.sh 1.0 KB runs code
- tools/emit_ir.sh 1.3 KB runs code
- tools/emit_rust_asm.sh 4.2 KB runs code
- tools/emit_rust_ir.sh 3.3 KB runs code
- tools/emit_rust_mir.sh 3.5 KB runs code
- tools/extract_compile_flags.py 8.6 KB runs code
- tools/generate_poc.py 47 KB runs code
- tools/mcp/apply_confidence_gates.py 3.3 KB runs code
- tools/mcp/check_mcp.sh 1.2 KB runs code
- tools/mcp/normalize_mcp_evidence.py 3.8 KB runs code
- tools/scripts/check_llvm_patterns.py 17 KB runs code
- tools/scripts/check_mir_patterns.py 19 KB runs code
- tools/scripts/check_rust_asm_aarch64.py 10 KB runs code
- tools/scripts/check_rust_asm_x86.py 9.4 KB runs code
- tools/scripts/check_rust_asm.py 16 KB runs code
- tools/scripts/find_dangerous_apis.py 14 KB runs code
- tools/scripts/semantic_audit.py 32 KB runs code
- tools/track_dataflow.sh 5.1 KB runs code
- tools/validate_rust_toolchain.sh 8.2 KB runs code
- workflows/phase-0-preflight.md 7.3 KB
- workflows/phase-1-source-analysis.md 4.7 KB
- workflows/phase-2-compiler-analysis.md 5.3 KB
- workflows/phase-3-interim-report.md 1.0 KB
- workflows/phase-4-poc-generation.md 1.2 KB
- workflows/phase-5-poc-validation.md 4.0 KB
- workflows/phase-6-final-report.md 1.0 KB
- workflows/phase-7-test-generation.md 769 B
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 · 372 lines · 57 tokens per session scan A 5fcd131e2509
zeroize-audit is a skill published in the GitHub repository Njones17/AI-agent-master-cyber-skills-list (21 stars, last pushed 6mo ago), with no licence file. It adds 57 tokens to every session and 5,497 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
memory-safety-patterns
Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.
compiler-frontend
Use when building a lexer, Pratt or recursive-descent parser, AST, symbol table, type checker, or LLVM IR emitter for a language or DSL. Not for optimizing IR: use llvm-passes.
custom-allocators
Use when implementing pool/slab/arena allocators, tuning jemalloc/mimalloc/tcmalloc, writing a Rust GlobalAlloc, or benchmarking allocator performance and fragmentation.
memory-safety-patterns
Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.
address-sanitizer
Use when building or running native code under AddressSanitizer, interpreting an existing ASan report, or debugging a memory-corruption failure. Not for remote or irreversible changes.
memory-model
C++ and Rust memory model skill for concurrent programming. Use when understanding memory ordering, writing lock-free data structures, using std::atomic or Rust atomics, diagnosing data races, or selecting the correct memory order for atomic operations. Activates on queries about memory ordering, acquire-release…