Borrowing it
Nothing to install: this file belongs to rahmanef63/connectors. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rahmanef63/connectors/main/.agents/skills/mcp-project-builder/SKILL.mdgit clone --depth 1 https://github.com/rahmanef63/connectorsWrote 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/rahmanef63/connectors/mcp-project-builder)<a href="https://agentmods.dev/skills/rahmanef63/connectors/mcp-project-builder"><img src="https://agentmods.dev/badge/skills/rahmanef63/connectors/mcp-project-builder/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/rahmanef63/connectors/mcp-project-builder"><img src="https://agentmods.dev/badge/skills/rahmanef63/connectors/mcp-project-builder.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 | $0.00061 | $0.01953 |
| Opus 5.5 | $0.00024 | $0.00781 |
| Sonnet 5.5 | $0.00012 | $0.00391 |
| Haiku 4.5 | $0.00006 | $0.00195 |
Grade A, and why
mcp-project-builder 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 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.
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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Project Builder
Use this skill when the task is to build, repair, or productionize an MCP integration in another project. The repository guides are the technical source of truth; this skill is the execution router.
Do not use this for a one-off MCP definition, a single connection setting, or a Custom GPT that only needs existing REST Actions.
Outcome
Deliver one host-agnostic MCP server plus the registration/package surfaces the target actually needs. “Done” means code, contract tests, security gates, deployment evidence, and a real host-facing acceptance flow agree.
0. Resolve the real target before editing
Record:
- canonical target repository, branch/SHA, framework and package manager;
- running/deployment owner, public HTTPS origin, reverse proxy and environment;
- existing auth/session model and how user/tenant identity is resolved;
- existing service/domain handlers that should remain the business-logic SSOT;
- target hosts: ChatGPT/Codex, Claude, Cursor, or another MCP client;
- required read/write/destructive outcomes, files/images, UI resources and long-running work;
- current MCP/plugin state, if any.
Never edit a generated build, dependency cache, temporary clone, or unrelated runtime because it is the first search hit.
Copy the planning template from assets/mcp-build-plan.md when the work spans more than a small patch.
1. Design the capability surface before transport
Read tool design.
Create a reviewed table for every proposed capability:
| Field | Required decision |
|---|---|
| primitive | tool, resource, prompt/skill, or not exposed |
| public name | stable, verb-clear, collision-safe |
| use / do-not-use | routing intent and confusable sibling |
| input | closed schema, descriptions, bounded enums/ids |
| identity | server-derived; never caller-supplied user/tenant |
| output | exact object envelope and next-call identifiers |
| authority | read/write plus destructive/idempotent/open-world truth |
| scope | least privilege required at list and call time |
| approval | whether the effect needs explicit human approval |
| limits | pagination, bytes, rate, timeout, retries |
What ships with it
4 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.
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 · 194 lines · 61 tokens per session scan A 167971d69b35
mcp-project-builder is a skill published in the GitHub repository rahmanef63/connectors (1 stars, last pushed 6d ago), licensed MIT. It adds 61 tokens to every session and 1,953 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
codex-with-chatgpt
A connection that lets ChatGPT help plan and review coding work while Codex edits files, runs commands, tests code, and handles execution.
codexless-browser-repair
Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…
migrate-waniwani-sdk-0.24-to-0.25
Migrate a project from @waniwani/sdk 0.24.x, or straight from 0.23.x, to 0.25.x. 0.25 removes the asked-only gate: the first question or widget lists every state field in fields, and any call writes a declared field whose value fits its Zod schema, so the flow skips the questions it fills. Computed values (price…
migrate-waniwani-sdk-0.23-to-0.24
Migrate a project from @waniwani/sdk 0.23.x to 0.24.x and auto-apply its breaking change to flows: the tool listing no longer names state fields under stateUpdates, start merges no stateUpdates, and continue and reset merge only fields the run has asked through an interrupt question or a widget's field. A field the…
add-widget
Add a new widget (React UI + MCP tool) to this template. Use when asked to "add a widget", "add a new tool with UI", "create a new widget", "scaffold a widget", or "build a new MCP App feature".
threebrowser-studio-mcp
Author, inspect, render, validate, animate, and save Three.js WebGPU projects in the native ThreeBrowser Studio through its real threestudio MCP tools. Use whenever Codex is asked to build or edit a ThreeBrowser Studio scene, material, Blender-style shader or texture graph, animation, lighting setup, camera, or…