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/enuno/dokployWrote 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/commands/enuno/dokploy/dokploy-create)<a href="https://agentmods.dev/commands/enuno/dokploy/dokploy-create"><img src="https://agentmods.dev/badge/commands/enuno/dokploy/dokploy-create/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/commands/enuno/dokploy/dokploy-create"><img src="https://agentmods.dev/badge/commands/enuno/dokploy/dokploy-create.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 | $0.00019 | $0.10584 |
| Opus 5.5 | $0.00008 | $0.04234 |
| Sonnet 5.5 | $0.00004 | $0.02117 |
| Haiku 4.5 | $0.00002 | $0.01058 |
Grade B, and why
dokploy-create scanned grade B 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 1mo 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/dokploy-* | wc -l Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
RUN wget [source-url] \ How it starts
The opening of the file, as written. The whole thing — 1,413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Dokploy Template (Skills-First + Cloudflare-First)
Create a complete, production-ready Dokploy template for $ARGUMENTS using progressive skill loading for optimal token efficiency. Defaults to Cloudflare services for all external integrations.
Invocation
/dokploy-create [application-name]
/dokploy-create [application-url] # GitHub/Docker Hub URL
Examples:
/dokploy-create gitea
/dokploy-create nextcloud
/dokploy-create https://github.com/paperless-ngx/paperless-ngx
/dokploy-create https://hub.docker.com/r/vaultwarden/server
Workflow Architecture
Multi-Phase Execution with Progressive Skill Loading:
┌─────────────────────────────────────────────────────────┐
│ Phase 1: Discovery (No Skills) │
│ • Research application (WebSearch, WebFetch) │
│ • Identify dependencies, storage needs, ports │
│ • DETECT: Custom build needed? │
│ • Output: Requirements document │
└───────────────────────┬─────────────────────────────────┘
│
├──[Custom Build Needed?]──┐
│ │
[No] │ [Yes│
│ │
│ ▼
│ ┌─────────────────────────────────────────┐
│ │ Phase 1.5: Custom Build (Conditional) │
│ │ • Check Dockerfiles/[app]/ exists │
│ │ • Create Dockerfile (if needed) │
│ │ • INVOKE: /create-container │
│ │ • Build → Push → Index Update │
│ │ • Output: registry.hashgrid.net/app:tag│
│ └───────────────────┬─────────────────────┘
│ │
└───────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ Phase 2: Architecture (Load: dokploy-multi-service) │
│ • Design service dependency graph │
│ • Plan network topology │
│ • SELECT CLOUDFLARE SERVICES (R2, Workers, D1, etc.) │
│ • Use custom image if built in Phase 1.5 │
│ • Output: Architecture design document │
└───────────────────────┬─────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ Phase 3: Generation (Load 6 Skills Progressively) │
│ 1. dokploy-compose-structure → Base YAML │
│ → Use registry.hashgrid.net/app:tag if custom │
│ 2. dokploy-traefik-routing → Routing labels │
│ 3. dokploy-health-patterns → Health checks │
│ 4. dokploy-cloudflare-integration → CF SERVICES ⭐ │
│ 5. dokploy-environment-config → Env vars │
│ 6. dokploy-template-toml → Template config │
│ • Output: Complete docker-compose.yml + template.toml │
└───────────────────────┬─────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ Phase 4: Validation (Load 2 Skills Sequentially) │
│ 1. dokploy-security-hardening → Security review │
│ 2. dokploy-template-validation → Convention check │
│ • Final: docker compose config (syntax validation) │
│ • Output: Validation reports + fixes │
└───────────────────────┬─────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ Phase 5: Documentation (No Skills) │
│ • Generate comprehensive README.md │
│ • Include Cloudflare setup guide (if applicable) │
│ • Note custom build if used from registry │
│ • Output: Complete documentation │
└───────────────────────┬─────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ Phase 6: Index Update (No Skills) │
│ • Update blueprints/README.md table │
│ • Insert in alphabetical order │
│ • Output: Updated repository index │
└─────────────────────────────────────────────────────────┘
Feedback Loops:
• Phase 3 ↔ Phase 4: Iterative refinement if validation fails
• Phase 2 → Phase 3: Architecture adjustments if needed
• Phase 1 → Phase 1.5: Trigger custom build if no official image
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.
- 1mo ago First seen · 1,413 lines · 19 tokens per session scan B 62daebf0706f
dokploy-create is a command published in the GitHub repository enuno/dokploy (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 19 tokens to every session and 10,584 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (enumerates other installed skills, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
create-docker-mcp-tunnel
Stand up an Anthropic MCP tunnel locally with Docker Compose so Claude can call a private MCP server (manual-credentials quickstart).
cloudflare-api
Hit the Cloudflare REST API for bulk, fleet, and operations wrangler can't do.
tanstack-start
Build a full-stack TanStack Start app on Cloudflare Workers from scratch.
cisco-isovalent-platform-setup
Install and operate Cilium networking and Tetragon runtime security on Kubernetes in OSS or Enterprise edition, with Hubble and Enterprise add-on paths. The coverage catalog explicitly maps newer Isovalent Enterprise Platform areas, including VM networking and Isovalent Load Balancer, to their supported, gated, or…
k8s-manifest
Generate production-ready Kubernetes manifests for the current application.
aci-run
Run a container in Azure Container Instances for quick one-off tasks or scheduled jobs.