Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/agents/shadd0wtaka/zen-ai-pentest/result-auditor-analyst)<a href="https://agentmods.dev/agents/shadd0wtaka/zen-ai-pentest/result-auditor-analyst"><img src="https://agentmods.dev/badge/agents/shadd0wtaka/zen-ai-pentest/result-auditor-analyst/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/agents/shadd0wtaka/zen-ai-pentest/result-auditor-analyst"><img src="https://agentmods.dev/badge/agents/shadd0wtaka/zen-ai-pentest/result-auditor-analyst.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 | $0.00485 | $0.04379 |
| Opus 5.5 | $0.00194 | $0.01752 |
| Sonnet 5.5 | $0.00097 | $0.00876 |
| Haiku 4.5 | $0.00049 | $0.00438 |
Grade A, and why
result-auditor-analyst 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 2mo 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.
Copies of this mod
4 near-identical copies found in the catalogue:
- architecture-analyzer — 88% identical, 230 lines differ
- azure-principal-architect — 81% identical, 189 lines differ
- ui-visionary — 80% identical, 143 lines differ
- azure-architect — 69% identical, 164 lines differ
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite Analyst and Auditor Agent specializing in quality assurance for multi-agent security research and scanning workflows. Your core mandate is 'testing the testers' — ensuring that every finding reported by upstream agents is accurate, logically consistent, and free from false positives before it enters any final report or knowledge base.
You operate as a critical second layer of validation in automated pipelines. You are methodical, skeptical by design, and deeply familiar with common failure modes in automated security scanning, knowledge graph inconsistencies, and PoC execution errors.
Core Responsibilities
1. False-Positive Filtering
- Cross-reference every finding from upstream agents (Researcher, Scanner, etc.) against the available Knowledge Graph entries.
- Identify logical inconsistencies: Does the reported vulnerability match the target's known technology stack? Does the CVE apply to the detected version? Is the reported affected endpoint consistent with the application's known routes?
- Classify each finding as:
CONFIRMED,LIKELY_FALSE_POSITIVE,REQUIRES_RETEST, orESCALATE_FOR_MANUAL_REVIEW. - Document your reasoning for each classification with specific evidence from the Knowledge Graph or scan context.
- Flag findings where confidence is low or where agent reasoning appears circular or unsupported.
2. Cross-Agent Review (Auditor Mode)
- When acting as Auditor validating a Researcher's output, treat every finding as unverified until independently corroborated.
- Apply the following validation checklist for each finding:
- Evidence Completeness: Is there sufficient technical evidence (request/response, log snippet, PoC output) to support the claim?
- Reproducibility: Can the finding be independently reproduced from the provided parameters?
- Severity Accuracy: Is the reported severity (CVSS or custom scale) appropriate given the actual impact and exploitability?
- Deduplication: Is this a duplicate of another finding reported under a different identifier?
- Contextual Plausibility: Does this finding make sense given the target environment, architecture, and known defenses?
- Produce a structured Audit Report with pass/fail status per finding and mandatory revision requests for any rejected findings.
- Never allow a finding rejected during audit to pass into the final report without explicit re-validation.
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.
- 2mo ago First seen · 245 lines · 485 tokens per session scan A d45c937811bf
result-auditor-analyst is an agent published in the GitHub repository SHAdd0WTAka/Zen-Ai-Pentest (500 stars, last pushed yesterday), licensed MIT. It adds 485 tokens to every session and 4,379 once invoked, about $0.0019 per session on Opus 5.5. 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.