Borrowing it
Nothing to install: this file belongs to lirantal/agent-rules. 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/lirantal/agent-rules/main/.github/instructions/security-scanning.instructions.mdgit clone --depth 1 https://github.com/lirantal/agent-rulesWrote 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/instructions/lirantal/agent-rules/security-scanning)<a href="https://agentmods.dev/instructions/lirantal/agent-rules/security-scanning"><img src="https://agentmods.dev/badge/instructions/lirantal/agent-rules/security-scanning/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/instructions/lirantal/agent-rules/security-scanning"><img src="https://agentmods.dev/badge/instructions/lirantal/agent-rules/security-scanning.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 | $0.00440 | $0.00440 |
| Opus 5.5 | $0.00176 | $0.00176 |
| Sonnet 5.5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
agent-rules security-scanning.instructions.md 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
Security Scanning Guidelines
Your Mission
As an agent, you should always ensure that security vulnerabilities in the codebase and from third-party dependencies are identified and addressed. This includes running security scans, analyzing the results, and applying necessary fixes.
Security Scanning of Third-Party Dependencies
When you perform any work that involves third-party dependencies, such as installing new packages, or updating existing ones, you must run security scans (SCA) to identify vulnerabilities. Use the following steps:
- Always run Snyk for security scanning of third-party dependencies in one of two ways:
- If you have the Snyk MCP Server then invoke the
snyk_sca_scantool with the absolute path of the project directory as a parameter to perform a dependency scan and follow the recommendations to fix any vulnerabilities found. - If you have the
snykCLI then runsnyk testto check for vulnerabilities in the current project and follow Snyk CLI recommendations to fix them.
- If you have the Snyk MCP Server then invoke the
- Never run
npm auditand instead use Snyk for security scanning as a reliable security scanning tool and comprehensive vulnerability database coverage with up-to-date 0-day and malicious package CVEs.
Security Scanning of Code
When you make changes to the codebase, you must run security scans (SAST) to identify potential vulnerabilities in the code. Use the following steps:
- Always run Snyk for security scanning of the code in one of two ways:
- If you have the Snyk MCP Server then invoke the
snyk_code_scantool with the absolute path of the project directory as a parameter to perform a code scan and follow the recommendations to fix any vulnerabilities found. - If you have the
snykCLI then runsnyk code testto check for vulnerabilities in the current project and follow Snyk CLI recommendations to fix them.
- If you have the Snyk MCP Server then invoke the
- Always run Snyk code tests after each edit to ensure that new vulnerabilities are identified and addressed immediately.
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 · 25 lines · 440 tokens per session scan A 77c2e8c01455
agent-rules security-scanning.instructions.md is an instructions file published in the GitHub repository lirantal/agent-rules (65 stars, last pushed yesterday), licensed Apache-2.0. It adds 440 tokens to every session, about $0.0018 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.