Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/avenoxai/avenoxbeyinnpx agentmods add skills/avenoxai/avenoxbeyin/beyin-doktorWrote 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/skills/avenoxai/avenoxbeyin/beyin-doktor)<a href="https://agentmods.dev/skills/avenoxai/avenoxbeyin/beyin-doktor"><img src="https://agentmods.dev/badge/skills/avenoxai/avenoxbeyin/beyin-doktor/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/skills/avenoxai/avenoxbeyin/beyin-doktor"><img src="https://agentmods.dev/badge/skills/avenoxai/avenoxbeyin/beyin-doktor.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 | $0.00109 | $0.04545 |
| Opus 5 | $0.00055 | $0.02273 |
| Sonnet 5 | $0.00022 | $0.00909 |
| Haiku 4.5 | $0.00011 | $0.00455 |
Grade C, and why
beyin-doktor scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Düzeltme: yedeği vault dışına taşı ve `chmod 600` ver; git izliyorsa Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
for h in session-start prompt-counter session-end pre-compact; do if grep -q "$h.sh" .claude/settings.json 2>/dev/null; then echo "$h: bagli"; else echo "$h: SETTINGS ICINDE YOK"; fi; done How it starts
The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Beyin Doktoru
Bu skill beynin mekanik katmanını denetler: hook'lar tetikleniyor mu, script'ler çalışmış mı, loglar tazeliğini koruyor mu, vault kirlenmiş mi. Amaç sessiz arızayı görünür yapmak.
Nasıl çalışırsın
- Vault kökünde (CLAUDE.md/AGENTS.md'nin bulunduğu klasör) çalış. Tüm yollar göreceli, mutlak yol yazma.
- Aşağıdaki kontrolleri Bash ile sırayla çalıştır. Komutları olduğu gibi kullan, tahmin etme.
- Her kontrolün çıktısını 🟢 / 🟡 / 🔴 olarak sınıfla.
- Sonucu tek bir tabloda ver, her 🔴 için bir düzeltme satırı yaz.
- En sonda tek cümlelik hüküm ver.
Kontroller salt okunurdur. Hiçbir şeyi kendiliğinden düzeltme, önce raporla, sonra kullanıcı isterse düzelt.
Kontroller
1. Hook dosyaları var mı ve çalıştırılabilir mi
for h in session-start prompt-counter session-end pre-compact; do f=".claude/hooks/$h.sh"; if [ ! -f "$f" ]; then echo "$h: DOSYA YOK"; elif [ ! -x "$f" ]; then echo "$h: calistirilabilir degil"; else echo "$h: ok"; fi; done
🟢 dördü de ok. 🔴 eksik veya çalıştırılabilir değil.
Düzeltme: chmod +x .claude/hooks/*.sh, dosya yoksa depodan kopyala.
2. Hook'lar settings.json içinde bağlı mı
for h in session-start prompt-counter session-end pre-compact; do if grep -q "$h.sh" .claude/settings.json 2>/dev/null; then echo "$h: bagli"; else echo "$h: SETTINGS ICINDE YOK"; fi; done
🟢 dördü de bağlı. 🔴 biri bile eksikse o hook hiç çalışmıyor demektir.
Düzeltme: .claude/settings.json içindeki hooks bloğuna eksik olayı ekle (SessionStart,
UserPromptSubmit, SessionEnd, PreCompact), sonra Claude Code'u yeniden başlat.
3. Özyineleme koruması her hook'ta var mı
for f in .claude/hooks/*.sh; do if grep -q 'BEYIN_INVOKED_BY' "$f"; then echo "$(basename "$f"): guard var"; else echo "$(basename "$f"): GUARD YOK"; fi; done
🟢 hepsinde var. 🔴 eksik. Guard'ı olmayan hook, arka plan claude -p çağrısında tekrar
tetiklenir ve sonsuz döngü riski doğar.
Düzeltme: dosyanın shebang'inden hemen sonraki satıra [ -n "${BEYIN_INVOKED_BY:-}" ] && exit 0 ekle.
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.
- 6d ago Changed · +29 lines 1a07918cabe2
- 11d ago First seen · 242 lines · 109 tokens per session scan C cd143814fb0d
beyin-doktor is a skill published in the GitHub repository avenoxai/avenoxbeyin (77 stars, last pushed 7d ago), licensed MIT. It adds 109 tokens to every session and 4,545 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.