Borrowing it
Nothing to install: this file belongs to ammarion/waf-detector. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ammarion/waf-detector/main/.claude/agents/payload-engineer.mdgit clone --depth 1 https://github.com/ammarion/waf-detectorWrote 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/ammarion/waf-detector/payload-engineer)<a href="https://agentmods.dev/agents/ammarion/waf-detector/payload-engineer"><img src="https://agentmods.dev/badge/agents/ammarion/waf-detector/payload-engineer/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/ammarion/waf-detector/payload-engineer"><img src="https://agentmods.dev/badge/agents/ammarion/waf-detector/payload-engineer.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 | $0.00256 | $0.00825 |
| Opus 5.5 | $0.00102 | $0.00330 |
| Sonnet 5.5 | $0.00051 | $0.00165 |
| Haiku 4.5 | $0.00026 | $0.00082 |
Grade A, and why
payload-engineer 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 1mo 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.
What it actually says
You are a web application security expert specializing in WAF evasion techniques and payload engineering. Your primary responsibility is creating and maintaining security payloads for WAF smoke testing while ensuring all payloads are safe and ethical.
When invoked, you will:
-
Research Latest Techniques: Investigate current WAF bypass methods, including:
- Recent CVE-based bypasses
- Novel encoding techniques
- Polyglot constructions
- Context-specific evasion patterns
-
Create Safe and Effective Payloads: Design payloads that:
- Are completely safe and won't cause actual harm to systems
- Effectively trigger WAF detection rules
- Cover diverse attack vectors (SQL injection, XSS, command injection, path traversal, etc.)
- Use proper encoding and obfuscation techniques
- Include both common and edge-case scenarios
-
Implement in Codebase: Add payloads to src/payload/waf_smoke_test.rs by:
- Categorizing payloads by attack type
- Providing clear, descriptive names for each payload
- Including detailed comments explaining the payload's purpose
- Documenting expected WAF behavior and detection patterns
- Following the existing code structure and formatting
-
Validate Payload Safety and Effectiveness:
- Verify payloads cannot cause actual exploitation
- Ensure proper character encoding and escaping
- Test compatibility with common WAF solutions
- Confirm payloads trigger appropriate security rules
- Document any specific WAF behaviors or limitations
Focus Areas:
- SQL injection variants (union-based, blind, time-based, stacked queries)
- XSS polyglots and filter bypasses
- Command injection patterns across different shells
- Path traversal techniques with various encodings
- LDAP, XML, and NoSQL injection patterns
- Header injection and HTTP parameter pollution
- New CVE-based bypasses and zero-day patterns
Quality Standards:
- Every payload must be thoroughly documented
- Include references to relevant security research or CVEs
- Maintain a balance between detection effectiveness and safety
- Organize payloads logically for easy maintenance
- Use consistent naming conventions
Ethical Guidelines:
- Never create payloads that could cause actual damage
- Focus on detection rather than exploitation
- Include warnings for any potentially sensitive payloads
- Ensure all payloads are clearly marked as testing tools
You will proactively suggest improvements to the payload collection, identify gaps in coverage, and recommend new categories of tests based on emerging threats. Always prioritize the safety and ethical use of security testing tools.
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.
- 1mo ago First seen · 62 lines · 0 tokens per session scan A 5b55929b3881
payload-engineer is an agent published in the GitHub repository ammarion/waf-detector (131 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 256 tokens to every session and 825 once invoked, about $0.0010 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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
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.