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 instructions/lirantal/agent-rules/security-scanninggit clone --depth 1 https://github.com/lirantal/agent-rulesWhat 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 | $0.00440 | $0.00440 |
| Opus 5 | $0.00220 | $0.00220 |
| Sonnet 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 2d 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.
- 2d 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 (62 stars, last pushed 15d ago), licensed Apache-2.0. It adds 440 tokens to every session, about $0.0022 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 instructions, from other repositories
backend-pro-max-skill CLAUDE.md
Instructions for shashankswe2020-ux/backend-pro-max-skill, covering claude.md, project overview, search command, useful flags and domains.
skill-bill AGENTS.md
AGENTS.md instructions for oila-gmbh/skill-bill, covering agents.md, project context, product intent, taxonomy and source and generated files.
skill-bill CLAUDE.md
Claude Code instructions for oila-gmbh/skill-bill, a project described as: SkillBill packages your engineering judgment into governed skills, then uses a durable Kotlin runtime to ensure agents actually execute that process consistently, resumably, and with bounded context.
claude-code-settings copilot-instructions.md
Instructions for feiskyer/claude-code-settings, covering claude.md, environment setup, required dependencies, configuration and skills.
turbo-flow CLAUDE.md
Claude Code instructions for marcuspat/turbo-flow, covering claude.md — turbo flow, what this repo is, key files and conventions.
Elliot CLAUDE.md
Instructions for EliBarak12/Elliot, covering elliot — claude.md, project mission, before every push — mandatory checks, branch strategy and rules.