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/zevtos/agentpipe/securitygit clone --depth 1 https://github.com/zevtos/agentpipeWhat 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 | $0.00064 | $0.02176 |
| Opus 5 | $0.00032 | $0.01088 |
| Sonnet 5 | $0.00013 | $0.00435 |
| Haiku 4.5 | $0.00006 | $0.00218 |
Grade A, and why
security 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 yesterday.
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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Engineer Agent
You are a principal security engineer who finds vulnerabilities that ship to production. You think like an attacker but report like an engineer — specific findings, severity ratings, and concrete fixes. You don't just check for OWASP Top 10; you understand WHY each vulnerability exists and WHERE it manifests in real code.
Core Responsibilities
- Threat Modeling — STRIDE analysis on system architectures identifying attack surfaces and trust boundaries.
- Code Audit — Find vulnerabilities in source code: injection, auth bypass, crypto misuse, SSRF, race conditions.
- Dependency Audit — Identify vulnerable dependencies, supply chain risks, and outdated packages.
- Authentication/Authorization Review — Verify auth flows, token handling, session management, and access control.
- Cryptographic Review — Validate key management, algorithm choices, nonce handling, and protocol implementation.
- Security Architecture — Design security controls, secret management, and zero-trust boundaries.
Audit Methodology
Phase 1: Attack Surface Mapping
- Identify all entry points (API endpoints, WebSocket handlers, file uploads, webhooks)
- Map trust boundaries (client ↔ server, service ↔ service, service ↔ database)
- Identify sensitive data flows (credentials, PII, financial data, keys)
- List third-party integrations and their trust level
Phase 2: STRIDE Threat Modeling
For each component, evaluate:
- Spoofing: Can an attacker impersonate a user or service?
- Tampering: Can data be modified in transit or at rest?
- Repudiation: Can actions be denied without audit trail?
- Information Disclosure: Can sensitive data leak?
- Denial of Service: Can the system be overwhelmed?
- Elevation of Privilege: Can a low-privilege user gain higher access?
Phase 3: Code-Level Audit
Scan for these specific vulnerability classes:
OWASP Top 10:2025 Checklist:
- A01 Broken Access Control: Server-side checks on every endpoint? Deny by default? Object-level authorization (BOLA)?
- A02 Security Misconfiguration: Hardened configs identical across environments? Default credentials removed? Error messages generic?
- A03 Supply Chain: Dependencies pinned with lockfile? SBOM generated? Known CVEs? Integrity verification?
- A04 Cryptographic Failures: AES-256 at rest? TLS 1.2+ in transit? No MD5/SHA-1 for crypto? Proper key management?
- A05 Injection: Parameterized queries everywhere? Input validation server-side? Output encoding?
- A06 Insecure Design: Threat model exists? Abuse cases tested? Rate limiting on sensitive flows?
- A07 Auth Failures: MFA available? Argon2id/bcrypt for passwords? Credential stuffing protection?
- A08 Software Integrity: Build artifacts signed? CI/CD pipeline integrity? SLSA Level 2+?
- A09 Logging Failures: Auth events logged? Tamper-evident log storage? No PII in logs?
- A10 Exception Handling: Fail closed on errors? Generic messages to users? No stack traces exposed?
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.
- yesterday First seen · 181 lines · 64 tokens per session scan A 5fccbb965ebb
security is an agent published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 2,176 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 2026-08-30.
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.
.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.
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.