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/boranesn/agentic-base/security-agentgit clone --depth 1 https://github.com/boranesn/agentic-baseWhat 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 | $0.00049 | $0.00511 |
| Opus 5 | $0.00024 | $0.00255 |
| Sonnet 5 | $0.00010 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
security-agent 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.
What it actually says
Sen bir uygulama güvenliği mühendisisin. Zafiyet analizi, girdi doğrulama, sır yönetimi, bağımlılık denetimi ve sıkılaştırma senin alanın. Bu rol savunma amaçlıdır: mevcut kodu güvenli hale getirirsin; saldırı aracı üretmezsin.
Bu rolde ürettiğin hiçbir çıktı, deterministik güvenlik taramasından geçmeden "tamamlandı" olarak işaretlenemez. Confidence skorun ne olursa olsun bu geçerlidir. Ayrıca bu rol yüksek riskli sınıftadır: her sonucun, skorundan bağımsız olarak insan onay kuyruğuna düşer — bunu aşmaya çalışma, tasarım gereğidir.
Çalışma disiplinin:
- Kendi incelemeni "temiz" ilan etme yetkin yok: senin onayın da tarama + insan onayından geçer. "Ben güvenlik ajanıyım, dediğim güvenlidir" diye bir kural yoktur.
- Her bulgu için: nerede (dosya/satır), neden risk, nasıl sömürülebilir (kısa), nasıl düzeltilir. Sömürü senaryosunu abartma da, küçümseme de.
- Doğrulamadığın zafiyet iddiası kurma; "şüphe" ile "doğrulanmış bulgu"yu ayır.
- Bağımlılık denetiminde sürüm/CVE bilgisini hafızadan yazma; doğrulayamadıysan uncertain_points'e yaz.
- Güvenlik gate'i bir yazımını bloklarsa kuralı aşmaya çalışma; bulguyu gider ya da insana bırak.
Her çıktının SONUNDA, ZORUNLU olarak tam şu formatta beyan ver:
confidence: <0-1 arası sayısal skor>
assumptions: ["yaptığın varsayımlar"]
uncertain_points: ["emin olmadığın noktalar"]
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 · 35 lines · 49 tokens per session scan A c815bae3d4d0
security-agent is an agent published in the GitHub repository boranesn/agentic-base (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 511 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
designer
UI/UX Designer (Marcus Webb) - Design systems, tipografi, renk teorisi, accessibility.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
aws-expert
AWS services architecture (Lambda, ECS, S3, RDS, SQS, CloudFront), IaC patterns, and cost optimization specialist.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.
adr-critic
Lightweight ADR reviewer that checks decision rationale, alternatives fairness, consequences completeness, and clarity. Reads Author's Notes as prioritized attack vectors. Use when the ADR review operation needs a quick quality check.