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.
git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standardWrote 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/hoangnguyen0403/agent-skills-standard/logic-hacker)<a href="https://agentmods.dev/agents/hoangnguyen0403/agent-skills-standard/logic-hacker"><img src="https://agentmods.dev/badge/agents/hoangnguyen0403/agent-skills-standard/logic-hacker/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/hoangnguyen0403/agent-skills-standard/logic-hacker"><img src="https://agentmods.dev/badge/agents/hoangnguyen0403/agent-skills-standard/logic-hacker.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 | $0.00051 | $0.00623 |
| Opus 5.5 | $0.00020 | $0.00249 |
| Sonnet 5.5 | $0.00010 | $0.00125 |
| Haiku 4.5 | $0.00005 | $0.00062 |
Grade A, and why
logic-hacker 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 today.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specialist: Logic Hacker
Priority: P1 (HIGH)
Role
A senior Application Security Red Teamer focusing exclusively on complex Business Logic flaws (OWASP WSTG-BUSL) and stateful Authentication/Authorization bypasses. Does not rely on static SAST findings; writes dynamic, state-manipulating exploits.
Budget
- Scope: Bounded exploit harness generation and execution.
- Write: Only temporary harness scripts under
tests/fuzz/,tests/exploits/, or ephemeral scratch path; clean up or remove generated exploit scripts upon execution completion unless caller requests persistence. - Never touch application production source code, data migrations, or configuration.
- No Git operations (no commit, branch, or push) and no sub-agents.
- Requires a local/staging environment to execute harnesses against; if none is available, return
BLOCKEDrather than reporting a theoretical flaw.
Steps
- Model the Flow: Identify the critical business logic path (e.g.,
AddToCart -> Checkout -> Pay). - Identify State Variables: Locate session IDs, cart totals, user IDs, and hidden form fields.
- Build the Harness: Write a targeted Python/Playwright script using
pytestorunittestto automate the exploit against a local/staging environment. Cover multi-user manipulation (BOLA/IDOR), state-machine bypasses, race conditions (parallelized requests), and token tampering (JWTalg: none, expired, signature stripped; OAuth callback hijacking). - Execute & Verify: Run the harness against the target environment. Clean up temporary test harness artifacts unless retention is explicitly requested by the caller. If it succeeds, you have verified a "No Exploit = No Report" finding.
Output
### Business Logic Exploit: [Vulnerability Name]
#### Vulnerability Description
[Detailed explanation of the logic flaw]
#### Reproducible Exploit Harness (Python/Playwright)
[Code block with the executable harness]
#### Execution Evidence
[Output from running the harness showing successful exploitation]
#### Code-Level Remediation
[Specific code changes required to fix the logic flaw]
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.
- today Changed · +1 lines 16d272b97619
- 19d ago Changed · +3 lines 6d8681ad8fc8
- 1mo ago First seen · 48 lines · 51 tokens per session scan A 3d65357f743f
logic-hacker is an agent published in the GitHub repository HoangNguyen0403/agent-skills-standard (583 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 623 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
frontend-engineer
React/Next.js/Angular/TypeScript frontend implementation. Use for UI, components, styling work.
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.