Skip to main content

53 posts tagged with "Devlog"

Devlog tag

View All Tags

mcp-web-setup: One CLI to Configure 18 MCP Servers Across Claude, Codex, and Gemini

· 5 min read
Victor Jimenez
Software Engineer & AI Agent Builder

Every AI coding tool has its own config format for MCP servers. Claude uses JSON, Codex uses TOML, Gemini uses a different JSON schema. Setting up the same 18 servers across all three means editing three files, remembering three formats, and hoping you didn't typo a credential. I built mcp-web-setup to do it once.

CPF: Compact Prompt Format — 30-50% Fewer Tokens, Zero Loss

· 10 min read
Victor Jimenez
Software Engineer & AI Agent Builder

LLM prompts are full of repeated English grammar. Every "If a module exists, then recommend it. Do NOT reinvent the wheel." burns tokens on words the model already understands. I built CPF (Compact Prompt Format) to replace that grammar with operators and abbreviations that LLMs decode natively — cutting token costs by 30-50% with zero runtime dependencies.

HTMX in Drupal Core: The Ajax API Replacement That Is Long Overdue

· 5 min read
Victor Jimenez
Software Engineer & AI Agent Builder

For over a decade, Drupal developers have relied on Drupal.ajax — a powerful but heavy abstraction layer over jQuery — to handle dynamic interactions. With jQuery's slow sunset and the rise of "HTML-over-the-wire" paradigms, the HTMX in Drupal Core initiative is the most sensible thing to happen to Drupal's frontend in years.

I built a proof-of-concept module to test what this migration actually looks like in practice.

Drupal AI Vulnerability Guardian: Triage 12 Vulnerability Patterns at Machine Speed

· 6 min read
Victor Jimenez
Software Engineer & AI Agent Builder

AI is making vulnerability discovery faster and cheaper. That is the easy part. The hard part is what happens next: an open-source maintainer with limited hours receives a flood of security reports and must decide which ones deserve immediate attention, which are false positives, and which can wait.

Gemini Ollama CLI Bridge: Local-First Code Analysis with Optional Cloud Refinement

· 6 min read
Victor Jimenez
Software Engineer & AI Agent Builder

Gemini Ollama CLI Bridge chains a local Ollama model with Google's Gemini into a two-stage code analysis pipeline. The first version piped data to Gemini through a shell subprocess -- fragile, hard to test, and impossible to cache. This upgrade replaces the shell integration with the google-generativeai Python SDK, adds result caching, and grows the test suite from 4 tests to 22.

Drupal AI Content Impact Analyzer: 6-Dimension Scoring That Tells Editors What to Fix

· 5 min read
Victor Jimenez
Software Engineer & AI Agent Builder

The first version of Drupal AI Content Impact Analyzer was a minimal proof-of-concept: a single scoring function, no tests, no documentation worth mentioning. It proved the idea worked. It did not prove the idea was useful to editors who need to know exactly why a piece of content scores the way it does. The upgrade rewrites the core into a 6-dimension scoring engine that tells editors precisely what to fix.

Drupal Entity Reference Integrity: Auto-Fix Broken References at Scale

· 5 min read
Victor Jimenez
Software Engineer & AI Agent Builder

The first version of drupal-entity-reference-integrity could scan a Drupal site and report broken entity references. That was the easy part. The hard part -- actually fixing them at scale without taking the site down -- was missing. This upgrade adds auto-fix mode, batch processing, and the test coverage needed to trust both in production.