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 commands/varienos/agentic-workflow/pre-deploy.skeletongit clone --depth 1 https://github.com/varienos/agentic-workflowWhat 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 | $0.00000 | $0.03996 |
| Opus 5 | $0.00000 | $0.01998 |
| Sonnet 5 | $0.00000 | $0.00799 |
| Haiku 4.5 | $0.00000 | $0.00400 |
Grade A, and why
pre-deploy.skeleton 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.
How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Deploy — Coolify Production Push Kontrolu
Coolify uzerinden production'a deploy oncesi tum kontrolleri calistirir, sonuc raporunu sunar. Kullanim:
/pre-deploy
Kural: OTONOM CALIS
- Kullaniciya soru SORMA — tum kontrolleri sirayla calistir.
- Hic bir seyi PUSH etme — sadece kontrol et ve raporla.
- Hata bulursan DUZELTME — raporla ve kullaniciya birak.
- Tum adimlari CALISTIR — bir adimi atlama.
Step 1 — Baslangic Kontrolu (Git Durumu + Branch)
cd ../Codebase && git status && git branch --show-current && git log --oneline -1
Kontrol et:
- Commit edilmemis degisiklik var mi?
- Hangi branch'tesin? (main/master disinda UYAR — Coolify genellikle main push'ta otomatik deploy yapar)
- Remote ile senkron mu? (
git statusciktisinda "ahead/behind" kontrolu)
Eger commit edilmemis degisiklik varsa:
FAIL: Commit edilmemis degisiklikler var. Once commit atilmali.
Eger branch main/master degilse:
WARN: Su an '{branch}' branch'indesin. Coolify otomatik deploy genellikle main branch'e push ile tetiklenir.
Step 2 — Degisiklik Ozeti
Son deploy'dan bu yana yapilan degisiklikleri listele:
cd ../Codebase && git log --oneline HEAD~20..HEAD
Degisiklikleri kategorize et:
- Yeni ozellikler (feat:)
- Hata duzeltmeleri (fix:)
- Yikici degisiklikler (breaking change iceren commit'ler)
- Veritabani degisiklikleri (migration iceren commit'ler)
- Altyapi degisiklikleri (Dockerfile, docker-compose, entrypoint.sh, CI/CD)
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 · 352 lines · 0 tokens per session scan A 97b76a6eb819
pre-deploy.skeleton is a command published in the GitHub repository varienos/agentic-workflow (58 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,996 tokens. 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 commands, from other repositories
toh-ship
Deploy app to production (Vercel, Netlify, and more).
deployment
Basic production deployment setup for FastAPI applications.
coolify-check-deployment
Check Coolify deployment status; file a high-priority task on a failed deploy. Passive — fixes nothing.
devops
Invoke the DevOps Engineer for cloud infrastructure, IaC (Terraform/OpenTofu), Kubernetes, CI/CD pipelines, containers, and deployment.
mlops
Invoke the MLOps Engineer for model serving & inference infrastructure, ML/AI pipelines, model deployment & monitoring, and infrastructure-level AI cost optimization.
wb-tailscale-status
Load directions via mcpwork-buddywbrun("agentdocs", {"path": "status/tailscale-status-directions", "depth": "full"}), then call mcpwork-buddywbrun("tailscalestatus").