IOSM v1.0 specification: reproducible methodology for continuous system improvement. Reference runtime implementation → github.com/rokoss21/iosm-cli
-
Updated
Mar 10, 2026 - Python
IOSM v1.0 specification: reproducible methodology for continuous system improvement. Reference runtime implementation → github.com/rokoss21/iosm-cli
Provide a terminal-based AI tool to perform controlled, measurable engineering tasks directly on real codebases.
A reusable AI-first development framework for building software with AI agents.
A practical framework for humans working with AI coding agents: outcome-first delivery, bounded scope, context economy, evidence-based review, traceability, and durable project knowledge.
任务架构通用智能体能力包 · 跨 Codex/Claude/Trae/Cursor 等 9+ 平台
One engineering workflow across Claude Code, Codex, Copilot, and Gemini CLI. A portable persona canon, process skills, and safety guardrails, kept in sync by design.
A constructional approach to engineering AI-powered workflow applications using TypeScript, SvelteKit, AWS CDK, Lambda, and a shared domain model.
Metodología portable y agnóstica de agentes para desarrollar software con IA de forma estructurada, verificable y transferible entre herramientas como Claude Code, Codex y OpenSpec.
Evidence-first methodology for disciplined AI-assisted software development with Claude
Practical methodology for disciplined AI-assisted software development with Codex in VS Code
How I run AI coding agents: the ticket that binds them, the policy that constrains them, and the second signature that lets their work merge.
A Claude Code harness and a knowledge-base format for building software with an AI assistant: rules, skills, hooks, and evidence-dated facts, derived from real installations.
Local-first authenticated browser automation for Claude Code — the Tap MCP server + skills. Record a logged-in browser task once; replay it forever in your own Chrome at zero LLM tokens.
A proof-driven, AI-accelerated method for taking infrastructure from idea to production — distilled from 3 production systems into drop-in templates (CLAUDE.md, rules, skills, commands, agents, hooks) for any project.
A governed methodology for AI-assisted software engineering built around explicit context, task contracts, deterministic verification, evidence, durable memory, reconciliation, and human control.
To associate your repository with the engineering-methodology topic, visit your repo's landing page and select "manage topics."