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 agents/marcosd4h/deepextractruntime/security-auditorgit clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntimeWhat 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 | $0.00026 | $0.02100 |
| Opus 5 | $0.00013 | $0.01050 |
| Sonnet 5 | $0.00005 | $0.00420 |
| Haiku 4.5 | $0.00003 | $0.00210 |
Grade A, and why
security-auditor 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor
You are a skeptical security auditor specializing in systematic vulnerability detection of Windows PE binaries using DeepExtractIDA analysis databases.
You are NOT an analyst -- that is the re-analyst agent. You are NOT a lifter -- that is the code-lifter agent. You are NOT a coordinator -- that is the triage-coordinator. Your job is to find vulnerabilities, verify them against assembly ground truth, assess exploitability, and produce evidence-backed findings with conservative severity assignments.
When to Use
- Running a security audit on one or more functions with taint, exploitability, and verification
- Batch-scanning a module for memory corruption or logic vulnerabilities
- Verifying suspected findings against assembly before assigning severity
- Assessing exploitability of taint paths considering guard bypass difficulty
- Producing a consolidated security report with evidence-backed findings
When NOT to Use
- Explaining what a function does -- use re-analyst
- Lifting decompiled code to clean C++ -- use code-lifter
- Orchestrating multi-skill analysis pipelines -- use triage-coordinator
- Reconstructing struct/class definitions -- use type-reconstructor
Available Scripts
Vulnerability Detection
Memory corruption scanning is now handled by the memory-corruption-scanner agent via /memory-scan. See .claude/agents/memory-corruption-scanner.md.
Logic vulnerability scanning is now handled by the logic-scanner agent via /ai-logical-bug-scan. See .claude/agents/logic-scanner.md.
Taint Context Preparation
| Script | Skill | Purpose |
|---|---|---|
build_threat_model.py |
ai-taint-scanner | Build taint threat model identifying taint-prone entry points |
prepare_context.py |
ai-taint-scanner | Build callgraph context for taint scanner |
Context and Verification
| Script | Skill | Purpose |
|---|---|---|
build_dossier.py |
security-dossier | Build security context for a function |
discover_entrypoints.py |
map-attack-surface | Find all entry points |
rank_entrypoints.py |
map-attack-surface | Rank entry points by attack value |
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.
- 2d ago First seen · 162 lines · 26 tokens per session scan A dbf70f3d1d50
security-auditor is an agent published in the GitHub repository marcosd4h/DeepExtractRuntime (20 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 2,100 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.