---
title: Context Driven Development
category: product
entity_type: skill
price: $15
canonical: https://forgehouse.ai/skills/context-driven-development/
lang: en
hreflang_alt: https://forgehouse.ai/tr/skiller/context-driven-development/
last_updated: 2026-06-20
---

# Context Driven Development

> When working with Conductor's context-driven development methodology, managing project context…

A disciplined methodology for managing project context as a first-class artifact that lives alongside your code, so AI assistants and team members always work from the same, current source of truth. It establishes five canonical context files: product vision, technology stack, workflow, work tracks, and communication guidelines, and keeps them synchronized as the project evolves. The result is consistent AI behavior across every session and faster onboarding for new engineers.

## Use cases
- Setting up a brand-new project so standards exist before any code is written
- Extracting implicit context from an existing codebase into documented artifacts
- Keeping AI assistants aligned across multiple development sessions
- Onboarding a new team member to an unfamiliar project quickly
- Deciding which document a new technical decision belongs in
- Running a context validation gate before starting a new work track

## Benefits
- AI assistants produce aligned output session after session instead of drifting
- New engineers reach productive output faster with explicit, readable context
- Decisions and their rationale survive team changes as institutional memory
- Stale-context rework is caught early instead of being built on wrong assumptions

## What’s included
- The Context to Spec & Plan to Implement workflow with phased execution
- Five canonical artifacts (product, tech-stack, workflow, tracks, guidelines) with clear ownership rules
- Artifact synchronization graph showing how a change in one file cascades to others
- Greenfield setup flow and brownfield context-extraction flow
- Context validation checklist run before each work track
- Anti-pattern catalog covering stale context, context sprawl, and over-specification

## Who it’s for
Engineering teams and AI-assisted developers who want consistent, persistent project context instead of scattered docs and ad-hoc prompts.

## How it runs
Product, stack, workflow, tracks, guidelines: five artifacts, each owning one question, no fact duplicated. The loop validates them before any work unit, propagates changes along dependencies and writes session state back afterward.
1. Establishes five canonical artifacts, each the single source of truth for one question: what and why (product), with what (tech stack), how to work (workflow), what is happening (tracks), and how to communicate (guidelines); the same fact is never duplicated across two files
2. Before any work unit starts, reads all artifacts and runs a validation checklist; stale information gets updated first, implementation second, because building on outdated assumptions is rewritten code
3. For existing codebases, extracts implicit context: package manifests fill the tech stack, CI configs fill the workflow, and undocumented working patterns get formalized rather than overwritten
4. Propagates every change along the dependency graph: a new feature triggers a dependency check, which triggers a workflow check, which spawns a tracked work unit
5. Couples documentation to commits: a dependency change without a matching tech-stack update raises a warning, and a completed track flips its feature from planned to implemented
6. At session end, writes progress, blockers and decisions back into the track plan, so the next session, human or AI, resumes from recorded state instead of someone's memory

## FAQ
### Does this only fit a brand-new project, or can I apply it to an existing codebase?
Both, because it sets up standards before code on a new project and can also extract implicit context out of an existing codebase into the same five files. Greenfield and legacy each have an entry point.

### How are these five files different from docs that always rot?
They are first-class artifacts that live next to the code and get updated as work happens, not a wiki you forget. Keeping them current is the discipline, and the payoff is people and AI assistants reading one source instead of guessing.

### Does it replace my issue tracker or enforce a process?
No, it defines the context layer of vision, stack, workflow and work tracks that your tracker and process sit on top of. It aligns everyone on the same truth, but it does not run your sprints for you.

## Price
$15, one-time, no subscription. VAT included.

Related guide: [AI and LLM engineering](https://forgehouse.ai/guides/ai-llm-engineering/)