kibuild-mcp: Command for Claude Code

.claude/commands/init-kibuild-project.md

init-kibuild-project is a command for Claude Code from KiBiz-Systems/kibuild-mcp. It costs 53 tokens per session (1,926 once invoked), scanned A, original, MIT.

A project-initialisation command for FileMaker projects that creates guide files for Claude, Codex-style agents, Gemini, and Cursor. The guides tell these tools to use KiBuild MCP, a FileMaker-aware interface, when exploring the project.

In plain words
What is it for?
Use it when starting AI-assisted work on a FileMaker project with KiBuild MCP. It creates the agent instruction files in the current project directory.
Why use it?
It gives different coding agents the same project instructions and helps them use FileMaker-specific searches instead of general command-line text searches. It also warns before replacing existing guide files.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is KiBiz-Systems/kibuild-mcp's own configuration. It tells Claude Code how to work on kibuild-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kibuild-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to KiBiz-Systems/kibuild-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/KiBiz-Systems/kibuild-mcp/main/.claude/commands/init-kibuild-project.md
Clone the repo
git clone --depth 1 https://github.com/KiBiz-Systems/kibuild-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for init-kibuild-project

README.md
[![agentmods](https://agentmods.dev/badge/commands/kibiz-systems/kibuild-mcp/init-kibuild-project.svg)](https://agentmods.dev/commands/kibiz-systems/kibuild-mcp/init-kibuild-project)
Your own site
<a href="https://agentmods.dev/commands/kibiz-systems/kibuild-mcp/init-kibuild-project"><img src="https://agentmods.dev/badge/commands/kibiz-systems/kibuild-mcp/init-kibuild-project.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,926 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.01926
Opus 5 $0.00026 $0.00963
Sonnet 5 $0.00011 $0.00385
Haiku 4.5 $0.00005 $0.00193

Measured 6d ago against content hash 01d8f25131a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

init-kibuild-project 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 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.

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.

.claude/commands/init-kibuild-project.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are initializing a FileMaker project to use KiBuild MCP tools as the primary AI interface. Generate all four guide files below in the current working directory.

If any file already exists, warn the user and ask before overwriting. Otherwise write all files automatically and report what was created.


File 1 — CLAUDE.md (Claude Code)

Write this content to CLAUDE.md:

# KiBuild MCP — Project AI Guide

This project uses the KiBuild MCP server for FileMaker-aware AI assistance.
**Always prefer KiBuild MCP tools over generic Bash, grep, or find.**

## Tool substitution rules

| Instead of... | Use this KiBuild MCP tool |
|---|---|
| `grep` for a script | `mcp__kibuild__find_script` |
| `grep` for a table | `mcp__kibuild__find_table` |
| `grep` for a layout | `mcp__kibuild__find_layout` |
| `grep` / `find` for keywords | `mcp__kibuild__search_index` |
| Reading XML files directly | `mcp__kibuild__xml_extract_steps` |
| `grep` for a name in XML | `mcp__kibuild__xml_lookup_name` |
| Tracing relationships manually | `mcp__kibuild__inspect_relationships` |
| `grep` for field usage | `mcp__kibuild__find_field_references_in_calculations` / `_in_scripts` / `_in_layouts` / `_in_relationships` |
| `grep` for script call sites | `mcp__kibuild__find_script_references_in_scripts` / `_in_layouts` |
| `grep` for layout references | `mcp__kibuild__find_layout_references_in_calculations` / `_to_scripts` / `_to_tables` / `_to_valuelists` |
| `grep` for variable usage | `mcp__kibuild__find_variable_references_in_scripts` |
| Running a FileMaker SQL query | `mcp__kibuild__execute_sql` |
| Writing generated output | `mcp__kibuild__write_outbox_artifact` |

## Start every FileMaker session with

1. `mcp__kibuild__load_skill` — load the specialist skill for the task
2. `mcp__kibuild__search_index` — orient in the schema before diving in
3. Never `grep` or `cat` raw XML — use `xml_extract_steps` instead

## Other tools

- `mcp__kibuild__generate_schema_map` — rebuild index after an XML export
- `mcp__kibuild__list_workflows` / `mcp__kibuild__get_workflow` — available workflows
- `mcp__kibuild__validate_fmxmlsnippet` — validate generated FileMaker XML
- `mcp__kibuild__propose_preview` — propose a UI/layout change with preview
- `mcp__kibuild__run_script` — execute a FileMaker script via plugin

Read the full file on GitHub · 181 lines

Changes

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.

  1. 6d ago First seen · 181 lines · 53 tokens per session scan A 01d8f25131a0

Subscribe to this mod's changes

init-kibuild-project is a command published in the GitHub repository KiBiz-Systems/kibuild-mcp (6 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 1,926 once invoked, about $0.0003 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 2026-08-31.