Skip to content
voodootikigodvoodootikigod
Tagged

agents

agents

Stop Running the SDLC on Models That Aren't Human

The SDLC is 60 years of defenses against human failure modes. Models fail differently, and some of their flaws are superpowers wearing bug costumes.

· 8 min
agents

Two Human Gates and Everything Between Is Machine-Checked

Eight phases, exactly two mandatory human moments, deterministic gates between everything, and a spend curve shaped like a barbell.

· 9 min
agents

Tests Are the Spec in the Only Language the Builder Can't Argue With

Rails: why TDD becomes the load-bearing trust mechanism of agentic development, why the builder must never touch its own tests, and a field catalog of how agents game gates.

· 8 min
agents

Prosecution, Not Code Review

Refute charters, findings-as-claims, loop-until-dry, and review-calibration, the tool that answers the question nobody asks: does your review stack actually catch anything?

· 7 min
agents

Three Dials: Parallel Agents Without Merge Hell

Cost, wall-clock, accuracy: the three dials of multi-agent orchestration, why they're coupled, why '3-5 agents' keeps showing up in field reports, and how to measure ambiguity instead of asking the model about it.

· 9 min
agents

The Lifecycle That Gets Cheaper Every Run

Distillation, the lessons ledger, skill rot, and the model ratchet: the compounding loop that bends the cost curve down, and the unit of account that makes it visible.

· 8 min
agents

The ADLC Toolkit

Eighteen gate-shaped tools, built by the lifecycle they enforce, plus the frontier-free doctrine, the honest loss account, and the adoption path that doesn't die in week two.

· 9 min
agents

ADLC vs. the Enterprise SDLC

A practical comparison between the Agentic Development Lifecycle and the traditional enterprise software development lifecycle: advantages, disadvantages, and where the two overlap.

· 11 min
agents

Prosecuting the Gates

I practiced what I preach and aimed the lifecycle's own prosecution phase at the toolkit that enforces it. Hardening my own gates surfaced the builder blind spots that normal testing missed—and proved why multi-layered structures, not trust, are the only way to ship reliable agentic software.

· 7 min
llm

Adversarial Review: For All, By All

adversarial-review brings skeptical, model-agnostic code review to your harness as the /adversarial-review skill, and to CI as a zero-dependency CLI. Either way, an independent LLM closes the loop the creator agent cannot close for itself.

· 8 min
agents

Skill Mining: Extracting What Your Codebase Already Knows

Your codebase already encodes how your team builds. Skill mining extracts that latent know-how into reusable agent skills. Here is the loop.

· 14 min
llm

Code Review Is Not Visual Review

AI coding agents are very good at producing working code quickly. The harder problem is whether that code has the right visual shape. I built gemini-plugin-cc to bring Gemini into the workflow as a design-review companion for Claude Code and agent skills.

· 5 min
llm

The Missing Quality Toolkit for Agent Skills

skill-versions solved staleness. But staleness was just the first symptom. Every package ecosystem — CPAN, RubyGems, PyPI, npm, Cargo — eventually builds the same quality infrastructure. Agent skills are just the next language. Meet skills-check.

· 10 min
llm

Your Agent's Knowledge Has a Shelf Life

Your Agent's Knowledge Has a Shelf Life and every day you ignore it, your agents and skills are likely drifting into error land or worse, silent failures. But we have seen this play before and I propose a fix for it. Meet skill-versions.com

· 6 min