Greenfield Run With Feedback Loop — Development skill for Claude Code
Instrumented AEF greenfield install — dual mandate (install AND falsify), local-first findings harness with a fixed record schema, TermLink publish with read-back verification, ranked unratified fix p.
How to install Greenfield Run With Feedback Loop
Installs to ~/.claude/skills/dimitrigeelen-agentic-engineering-framework-greenfield-run-with-feedback-loop/SKILL.md
mkdir -p ~/.claude/skills/dimitrigeelen-agentic-engineering-framework-greenfield-run-with-feedback-loop && curl -fsSL https://raw.githubusercontent.com/DimitriGeelen/agentic-engineering-framework/HEAD/prompts/greenfield-run-with-feedback-loop.md -o ~/.claude/skills/dimitrigeelen-agentic-engineering-framework-greenfield-run-with-feedback-loop/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Greenfield Run With Feedback Loop does
id: greenfield-run-with-feedback-loop name: "Greenfield run with feedback loop" description: "Instrumented AEF greenfield install — dual mandate (install AND falsify), local-first findings harness with a fixed record schema, TermLink publish with read-back verification, ranked unratified fix proposals" kind: agent tags: [onboarding, install, greenfield, findings, feedback-loop, falsification, termlink, instrumented] variables: [] created: 2026-08-13T00:00:00Z updated: 2026-08-13T00:00:00Z
Alternatives in Development
- Rank — /rank - Triage Scraped Jobs into a Ranked Shortlist 36.6k ★
- Breach Check — HIBP k-anonymity check on a password wordlist 4.5k ★
- Fidelity — Measure how faithfully a clone reproduces a site — pixel-diff plus motion-fidelity into one 0-100 score, a let 3.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Aef Fresh Install Onboarding
Install AEF on a machine and onboard a new/empty project — dogfood-hardened (T-2441): project-local fw, sessio
Langchain Debater
A multi-role debate agent built with LangGraph + Claude Sonnet 4.6, instrumented with dual tracing to LangSmit
Adlc Init
Launch the ADLC adoption wizard in this repo (dual-mode greenfield/brownfield setup).
Falsify
Adversarially falsify research findings via web-only disconfirming search; quarantine, downgrade, or annotate
Debrief Agent
Post-session review that proposes changes to the agent's environment — never to the code. Nine lenses over the
Ferret
Ferret: the ADE for feedback by voice and screen. Point at the real screen, say what's wrong, and hand Claude
Related Agents
Infra Base Scaffolder
Genera la infraestructura base del consumidor (8 modulos Terraform + esqueleto del entorno con outputs) en un
Release Guardian
Pre-publish release gate — blocks a crates.io publish if the CRATES list drifted, versions are inconsistent, t
Autopilot Orchestrator
Full RTL design pipeline orchestrator. Manages 6-phase flow with dual-layer phase gates, parallel agent execut