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 skills/agentfront/frontmcp/frontmcp-developmentnpx skills add agentfront/frontmcp --skill frontmcp-developmentgit clone --depth 1 https://github.com/agentfront/frontmcpWhat 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 | $0.00196 | $0.05713 |
| Opus 5 | $0.00098 | $0.02857 |
| Sonnet 5 | $0.00039 | $0.01143 |
| Haiku 4.5 | $0.00020 | $0.00571 |
Grade A, and why
frontmcp-development 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FrontMCP Development Router
Entry point for building MCP server components. This skill helps you find the right development reference based on what you want to build. It does not teach implementation details itself — it routes you to the specific reference (under references/) that does.
When to Use This Skill
Must Use
- Starting a FrontMCP development task and unsure which component type to build (tool vs resource vs prompt vs agent)
- Onboarding to the FrontMCP development model and need an overview of all building blocks
- Planning a feature that may require multiple component types working together
Recommended
- Looking up the canonical name of a development reference to install or search
- Comparing component types to decide which fits your use case
- Understanding how tools, resources, prompts, agents, and skills relate to each other
Skip When
- You already know which component to build (go directly to
create-tool,create-resource, etc.) - You need to configure server settings, not build components (see
frontmcp-config) - You need to deploy or build, not develop (see
frontmcp-deployment)
Decision: Use this skill when you need to figure out WHAT to build. Open the matching reference under
references/directly when you already know.
Prerequisites
- A scaffolded FrontMCP project (see
frontmcp-setupif you don't have one). - Familiarity with TypeScript decorators and Zod schemas — every component is decorator-driven and validates I/O via Zod.
- Decide whether you're adding to an existing
@Appor composing a new one (multi-app projects: seemulti-app-composition).
Steps
This is a router skill. The "steps" here are how to choose the right reference (a markdown file under references/), not how to implement a component.
- Identify the component type using the Scenario Routing Table below.
- Open the matching reference (e.g.
references/create-tool.md,references/create-resource.md) and follow its Steps section. - Compose, if needed: most non-trivial features need two or more components (e.g. tool + provider, resource + adapter). Read each reference independently before wiring them together.
- Test before integration (
frontmcp-testing) — every component type has a unit-test recipe.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/create-adapter/basic-api-adapter.md 2.7 KB
- examples/create-adapter/namespaced-adapter.md 3.9 KB
- examples/create-agent-llm-config/anthropic-config.md 2.4 KB
- examples/create-agent-llm-config/openai-config.md 2.5 KB
- examples/create-agent/basic-agent-with-tools.md 3.6 KB
- examples/create-agent/custom-multi-pass-agent.md 3.1 KB
- examples/create-agent/nested-agents-with-swarm.md 4.0 KB
- examples/create-job/basic-report-job.md 2.7 KB
- examples/create-job/job-with-permissions.md 3.5 KB
- examples/create-job/job-with-retry.md 2.6 KB
- examples/create-plugin-hooks/basic-logging-plugin.md 2.0 KB
- examples/create-plugin-hooks/caching-with-around.md 2.2 KB
- examples/create-plugin-hooks/tool-level-hooks-and-stage-replacement.md 3.4 KB
- examples/create-plugin/basic-plugin-with-provider.md 1.9 KB
- examples/create-plugin/configurable-dynamic-plugin.md 5.3 KB
- examples/create-plugin/plugin-with-context-extension.md 3.8 KB
- examples/create-prompt/basic-prompt.md 2.2 KB
- examples/create-prompt/dynamic-rag-prompt.md 3.0 KB
- examples/create-prompt/multi-turn-debug-session.md 2.8 KB
- examples/create-provider/basic-database-provider.md 4.5 KB
- examples/create-provider/config-and-api-providers.md 6.6 KB
- examples/create-resource/basic-static-resource.md 2.0 KB
- examples/create-resource/binary-and-multi-content.md 3.2 KB
- examples/create-resource/parameterized-template.md 2.7 KB
- examples/create-skill-with-tools/basic-tool-orchestration.md 2.6 KB
- examples/create-skill-with-tools/directory-skill-with-tools.md 4.1 KB
- examples/create-skill-with-tools/incident-response-skill.md 3.4 KB
- examples/create-skill/basic-inline-skill.md 2.9 KB
- examples/create-skill/directory-based-skill.md 3.7 KB
- examples/create-skill/parameterized-skill.md 3.4 KB
- examples/create-workflow/basic-deploy-pipeline.md 2.3 KB
- examples/create-workflow/parallel-validation-pipeline.md 3.3 KB
- examples/create-workflow/webhook-triggered-workflow.md 4.1 KB
- examples/decorators-guide/agent-skill-job-workflow.md 4.5 KB
- examples/decorators-guide/basic-server-with-app-and-tools.md 4.0 KB
- examples/decorators-guide/multi-app-with-plugins-and-providers.md 5.1 KB
- examples/official-plugins/cache-and-feature-flags.md 3.7 KB
- examples/official-plugins/production-multi-plugin-setup.md 4.9 KB
- examples/official-plugins/remember-plugin-session-memory.md 3.3 KB
- examples/openapi-adapter/authenticated-adapter-with-polling.md 2.8 KB
- examples/openapi-adapter/basic-openapi-adapter.md 1.7 KB
- examples/openapi-adapter/format-resolution-and-custom-resolvers.md 3.6 KB
- examples/openapi-adapter/multi-api-hub-with-inline-spec.md 4.3 KB
- examples/openapi-adapter/ref-security-and-filtering.md 4.7 KB
- references/create-adapter.md 8.2 KB
- references/create-agent-llm-config.md 2.0 KB
- references/create-agent.md 26 KB
- references/create-job.md 27 KB
- references/create-plugin-hooks.md 20 KB
- references/create-plugin.md 22 KB
- references/create-prompt.md 17 KB
- references/create-provider.md 19 KB
- references/create-resource.md 21 KB
- references/create-skill-with-tools.md 30 KB
- references/create-skill.md 26 KB
- references/create-workflow.md 27 KB
- references/decorators-guide.md 47 KB
- references/official-adapters.md 4.5 KB
- references/official-plugins.md 28 KB
- references/openapi-adapter.md 22 KB
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 · 289 lines · 196 tokens per session scan A 8dc9e04b0c41
frontmcp-development is a skill published in the GitHub repository agentfront/frontmcp (147 stars, last pushed 26d ago), licensed Apache-2.0. It adds 196 tokens to every session and 5,713 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
a0-development
Development guide for extending Agent Zero from current source and DOX. Use for framework architecture, tools, extensions, API/WebUI handlers, agent profiles, prompts, skills, projects, runtime boundaries, and contribution workflow. Load the focused reference files before giving implementation guidance.
a0-development
Development guide for extending and building features for the Agent Zero AI framework. Covers architecture, tools, extensions, API endpoints, agent profiles, projects, prompts, and skills — with correct paths, imports, and patterns matching the current codebase.
agent-development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
reflection-coach
Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change. Use for evidence-backed coaching proposals, never hot-swaps.
openai-knowledge
Use when working with the OpenAI API (Responses API) or OpenAI platform features (tools, streaming, Realtime API, auth, models, rate limits, MCP) and you need authoritative, up-to-date documentation (schemas, examples, limits, edge cases). Prefer the OpenAI Developer Documentation MCP server tools when available…
agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues…