Genexus18MCP: Instructions file for Gemini CLI

GEMINI.md

Genexus18MCP GEMINI.md is an instructions file for Gemini CLI from lennix1337/Genexus18MCP. It costs 2,288 tokens per session, scanned A, original, MIT.

Repository instructions for using GeneXus MCP, a protocol for discovering and reading knowledge-base objects through tools and resources.

In plain words
What is it for?
Initializing MCP sessions, discovering available tools and resources, querying GeneXus objects, and reading their source or metadata.
Why use it?
They clarify the current MCP request flow and warn that an older API endpoint is no longer supported.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is lennix1337/Genexus18MCP's own configuration. It tells Gemini CLI how to work on Genexus18MCP 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 Genexus18MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lennix1337/Genexus18MCP. 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/lennix1337/Genexus18MCP/main/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/lennix1337/Genexus18MCP

Made for: Gemini CLI.

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 Genexus18MCP GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lennix1337/genexus18mcp/gemini-md/github.svg)](https://agentmods.dev/instructions/lennix1337/genexus18mcp/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/lennix1337/genexus18mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/lennix1337/genexus18mcp/gemini-md/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.

agentmods 80×15 button for Genexus18MCP GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lennix1337/genexus18mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/lennix1337/genexus18mcp/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,288 This file is loaded in full into every session.
When invoked 2,288 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.02288 $0.02288
Opus 5.5 $0.00915 $0.00915
Sonnet 5.5 $0.00458 $0.00458
Haiku 4.5 $0.00229 $0.00229

Measured 2d ago against content hash 01a2bb786ac1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Genexus18MCP GEMINI.md 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.

GEMINI.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GeneXus MCP Protocol Guide

Required repo skills before editing KB logic:

  1. GeneXus MCP Mastery
  2. GeneXus 18 Guidelines

This repository is MCP-first. The official transport is MCP over stdio or HTTP at /mcp. The old /api/command endpoint is no longer part of the gateway surface.

Correct MCP flow

  1. Initialize the session with initialize.
  2. Discover the live surface with tools/list, resources/list, resources/templates/list, prompts/list, and completion/complete when needed.
  3. Execute work with tools/call, resources/read, and prompts/get.
  4. For HTTP MCP, send MCP-Protocol-Version: 2025-06-18 and reuse the returned MCP-Session-Id.
  • genexus_wire (MANDATORY FIRST STEP): native Rust architectural discovery and call graph engine (sub-10ms). Run action=pack_task or for BEFORE reading large objects or editing KB code to orient on any task, rank affected symbols, and calculate blast radius under a strict token budget. Actions: pack_task (default), status, for (with domain synonym expansion, e.g. fat->faturamento, cli->cliente), callers, impact, path (shortest call path from from to to), slice, safe_delete, index, doctor. Formats: toon (token-efficient tabular ~40% savings, recommended), mermaid (renders flowchart/diagram for markdown artifacts), xml, json. On a native KB only pack_task works without an export: pass targets (object names) and/or name the objects in task; it returns the resolved objects with direct callers/callees and lists what it could not resolve.
  • genexus_query: find objects, references, signatures, and dependency entry points. Supports optional typeFilter and domainFilter for server-side narrowing.
  • genexus_read: read object parts with pagination. Pass singular name for one object or targets[] for coordinated multi-object reads (mutually exclusive). For MCP clients, keep reads paginated; the server intentionally returns a source-first first page when no explicit offset/limit is provided. For XML metadata parts such as Layout, WebForm, and PatternInstance, the gateway applies a larger metadata budget to avoid truncating the editable XML.
  • genexus_edit: apply focused edits to a part or replace content through the MCP write path. Three modes:
    • mode: 'xml' (default): full XML replacement.
    • mode: 'ops': typed semantic op catalog (set_attribute, add_attribute, remove_attribute, add_rule, remove_rule, set_property).
    • mode: 'patch': JSON-Patch (RFC 6902) array over the canonical JSON object representation; legacy string-form text patch is also accepted for backward compatibility. Pass targets[] (array of edit-request objects) for atomic multi-object edits — mutually exclusive with singular name. PatternInstance targets the authoritative WorkWithPlus instance when the requested object is a WebPanel managed by WorkWithPlus.
  • All write tools (genexus_edit, genexus_create_object, genexus_refactor, genexus_forge, genexus_import_object) accept:
    • dryRun: true — returns a preview envelope {_meta:{dryRun,schemaVersion}, plan:{touchedObjects, xmlDiff, brokenRefs, warnings}} without mutating the KB.
    • idempotencyKey: '<token>' ([A-Za-z0-9_-]{1,128}) — deduplicates retries; concurrent calls with the same key are coalesced; cache is per-KB, sliding TTL 15 min default. dryRun bypasses the cache.
  • genexus_inspect: get structured conversion or object context.
  • genexus_analyze: one tool with mode: linter | navigation | hierarchy | impact | data_context | ui_context | pattern_metadata | summary | explain. explain is compatibility-only: it preserves the legacy envelope and returns NotImplemented; use summary for a concise object overview, context for 360° task context, or genexus_read for source. The standalone genexus_summarize and genexus_explain_code were replaced in v2.3.0.
  • genexus_lifecycle: build, validate, index, and KB lifecycle operations.
  • genexus_sql: action=ddl for Transaction/Table DDL or action=navigation for the SQL of a procedure's For Each (replaces genexus_get_sql and genexus_get_sql_for_navigation in v2.3.0).
  • genexus_kb: multi-KB pool management (action: list | open | close | set_default). Replaces genexus_open_kb in v2.3.0.
  • genexus_create_object: create new KB objects.
  • genexus_refactor: supported rename and extraction refactors.
  • genexus_add_variable: add variables through the worker contract.
  • genexus_format: format source through the worker formatter.
  • genexus_properties: get or set object properties.
  • genexus_asset: find, read, and write KB assets such as .xlsx templates. Reads are metadata-first; request includeContent=true only for files small enough to carry as Base64 safely.
  • genexus_history: list, read, save, and restore object history.
  • genexus_structure: read or update logical and visual structure.
  • genexus_doc: access documentation, health, and visualization flows.

Read the full file on GitHub · 100 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. 2d ago Changed · +50 tokens per session 01a2bb786ac1
  2. 11d ago Changed · +1 lines · +174 tokens per session 47b235b333e8
  3. 1mo ago Changed · +1 lines · +13 tokens per session cceec9bf276e
  4. 1mo ago Changed · +4 lines · +116 tokens per session 6bdd42f8ae8a
  5. 1mo ago Changed · +8 lines · +133 tokens per session bca42395217d
  6. 1mo ago First seen · 86 lines · 1,802 tokens per session scan A ad75c24dd0c0

Subscribe to this mod's changes

Genexus18MCP GEMINI.md is an instructions file published in the GitHub repository lennix1337/Genexus18MCP (38 stars, last pushed yesterday), licensed MIT. It adds 2,288 tokens to every session, about $0.0092 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 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,549 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens