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/bordenet/golden-agentsWrote 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/rules/bordenet/golden-agents/security)<a href="https://agentmods.dev/rules/bordenet/golden-agents/security"><img src="https://agentmods.dev/badge/rules/bordenet/golden-agents/security/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/rules/bordenet/golden-agents/security"><img src="https://agentmods.dev/badge/rules/bordenet/golden-agents/security.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 | $0.00375 | $0.00375 |
| Opus 5.5 | $0.00150 | $0.00150 |
| Sonnet 5.5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00038 | $0.00038 |
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 5d 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 Workflow
Priority: CRITICAL - a leaked secret is not fixed by rewriting the sentence later.
Source: codebase-reviewer, scripts AGENTS.md, security-upgrade skill
🔒 Pre-Commit Hooks - NEVER BYPASS
Pre-commit hooks exist to protect intellectual property. NEVER disable or bypass them.
# ❌ NEVER DO THIS
git commit --no-verify
# ✅ ALWAYS DO THIS
git commit # Let hooks run
Security Scanning Tools
| Language | Tool | Command |
|---|---|---|
| Node.js | npm audit | npm audit --json |
| Go | govulncheck | govulncheck ./... |
| Python | pip-audit | pip-audit -r requirements.txt |
Security Upgrade Workflow
- Discovery - Identify projects with dependencies
- Scan - Run security scanners
- Upgrade - Fix vulnerabilities
- Validate - Compile, test, verify
- Re-scan - Confirm fixes
- Commit - Push with green CI
CVE Response Priority
| Severity | Response Time |
|---|---|
| Critical | Immediate |
| High | Same day |
| Moderate | Within week |
| Low | Next release |
Secret Management
- NEVER commit secrets to git
- Use environment variables for API keys
- Store secrets in secure credential managers
- Use
.env.localfiles (gitignored) - Prompt for secrets interactively in setup scripts
Related Skills
For comprehensive security workflows:
superpowers-plus/skills/security-upgrade/
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.
- 5d ago First seen · 64 lines · 375 tokens per session scan A dba9f916a78b
security is a cursor rule published in the GitHub repository bordenet/golden-agents (2 stars, last pushed 3d ago), licensed MIT. It adds 375 tokens to every session, about $0.0015 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 2026-11-12.
security compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| securitybordenet/golden-agents | Cursor rule | 2 | 3d ago | MIT | A | 375 | Cursor |
| commitsm3au/playwright-bdd-cursor-template | Cursor rule | 2 | 6d ago | MIT | A | 0 | Cursor |
| no-ai-contributorsuwaserver/uwas | Cursor rule | 138 | 3d ago | none | A | 177 | Cursor |
| git-workflowuseshape/Shape | Cursor rule | 34 | yesterday | none | A | 174 | Cursor |
| conventional-commitsssoriche/dotfiles | Cursor rule | 7 | 7d ago | none | A | 0 | Cursor |
| git-disciplinemennyg19-cmyk/MasterGenAIInstructions | Cursor rule | 2 | today | none | A | 656 | Cursor |
| git-commit-standardsivangrynenko/cursorrules | Cursor rule | 88 | 1y ago | MIT | A | 0 | Cursor |