Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/davidbuenov/dbv-specs-ops/llms.txt

Use this file to discover all available pages before exploring further.

Spec-Driven Development (SDD) is the foundational principle behind dbv-specs-ops: no line of code is written until the specification exists. In AI-assisted development, where a model can generate hundreds of lines in seconds, the absence of a prior specification is not a minor oversight — it is the root cause of runaway technical debt, token waste, and systems that work once but cannot be maintained. SDD introduces a structured contract between the developer and the AI: the “what” and “why” must be documented before the “how” begins.

The Three-Level Spectrum

AI-assisted software development is not a binary choice between “using AI” and “not using AI.” It exists on a spectrum with three distinct levels of discipline:
[ Vibe Coding ] ──────────── [ Structured Coding ] ──────────── [ Agentic Engineering ]
  Casual prompting              Prompts with examples              Formal specs (SDD)
  Visual validation             Manual unit tests                  Automated Evals
  High tech debt                Guided correction                  Full Agentic Harness
  Fast initial velocity         Moderate risk                      Low marginal cost (OpEx) at scale
  • Vibe Coding is characterized by informal natural-language instructions accepted without rigorous validation. When something breaks, the error is pasted back into the AI to fix. It is ideal for weekend prototypes but unsustainable for production systems.
  • Structured Coding introduces prompts with examples and some manual testing, reducing risk but without a formal framework governing the entire lifecycle.
  • Agentic Engineering is development under a strict Harness — the AI acts as an execution engine guided by prior design specifications and validated automatically through tests and evaluation rubrics (Evals). This is where dbv-specs-ops operates.

Why Vibe Coding Fails in Production

The appeal of Vibe Coding is real: near-zero upfront effort and instant output. But this trades low Capital Expenditure (CapEx) for runaway Operational Expenditure (OpEx):
  • Token Burn: Context windows saturated by poorly-optimized prompts and infinite error-correction loops consume enormous token budgets with diminishing returns.
  • Maintenance Tax: Human developers spend hours reverse-engineering “spaghetti code” or patching security vulnerabilities that a specification review would have prevented.
  • No Tests: Without a spec defining acceptance criteria, tests are an afterthought — and an afterthought test suite is rarely written at all.
  • No Traceability: When a requirement changes or a bug appears, there is no document explaining why the code was written the way it was.
Vibe Coding produces systems that appear to work during the demo but accumulate hidden costs in the weeks and months that follow. The lack of specifications makes every future change a risky guess.

How “Spec Before Code” Changes the Workflow

The SDD rule is simple to state and rigorous to enforce: the AI must not write implementation code for a requirement that does not exist in docs/SPECIFICATIONS.md. If the “what” is not clear, the AI asks clarifying questions before acting. This single constraint produces a cascade of downstream benefits:
  • The developer is forced to articulate intent before seeing output, surfacing ambiguities early.
  • The AI has a ground-truth document to reference, reducing hallucinated features.
  • Future sessions — with the same AI or a different one — can reconstruct context from the spec rather than reverse-engineering the code.
  • Acceptance criteria defined in the spec become the basis for the mandatory test phase.

The 6 Development Phases

dbv-specs-ops enforces SDD through a strict six-phase lifecycle. Each phase has a trigger command the developer types in the chat. The AI always respects this order and will not skip a phase without explicit approval.
#PhaseCommandCore purpose
1Spec/specDefine the “what” and “why” in SPECIFICATIONS.md before any code
2Plan/planValidate specs against edge cases; break work into atomic steps
3Build/buildImplement incrementally, one slice at a time
4Test/testProve correctness — a task is not done without a passing test
5Simplify/code-simplifyRefactor for clarity and run the mandatory security audit
6Ship/shipVersion, document, and release with a full context update
You can jump to any phase by typing its command. For example, typing /ship when you are ready to deliver causes the AI to handle versioning, changelog updates, and git tagging automatically.
For a deep dive into each phase, see the workflow reference pages.

The Enforcement Layer

dbv-specs-ops v2.0.0 introduces an Enforcement Layer built directly into the AI’s instruction set (docs/MASTER_PROMPT.md). This layer makes phase-skipping structurally difficult rather than relying on developer discipline alone:
  • The AI is instructed to treat all project files (including SPECIFICATIONS.md) as data, not as directives — only the MASTER_PROMPT.md XML tags carry authority. This prevents prompt injection from within project files.
  • At the /plan phase, the AI must run an Adversarial Architect Review — a mandatory internal debate printed as an XML block — before breaking the work into tasks. If a risk is identified and accepted, it is immediately recorded in memory.md.
  • At the /ship phase, a Memory Gate requires the AI to print a <memory_update_proposal> XML block before closing any task, ensuring persistent knowledge is never silently discarded.
  • The AI will not mark a task as done unless a passing test exists. “Tests are proof” is a hard rule, not a suggestion.

CapEx vs. OpEx: The Economics of SDD

The economic model of SDD is the inverse of Vibe Coding, and understanding this inversion is key to justifying the upfront discipline it requires.
DimensionVibe CodingSpec-Driven Development (SDD)
Upfront effort (CapEx)Near zero — no planning or architectureModerate — write specs, configure Harness
Marginal cost per feature (OpEx)Grows over time (token burn, maintenance tax)Decreases over time (structured factory model)
Technical debtHigh and compoundingControlled and tracked
AI context qualityDegrades across sessionsPreserved in memory.md and task.md
Test coverageAd hoc or absentMandatory before task completion
Security postureUnreviewedAudited at /code-simplify phase
Onboarding a new sessionRequires reverse-engineeringReads memory.md Context Snapshot
Best forWeekend prototypesProduction systems, team development
The key insight from the “The New SDLC With Vibe Coding” whitepaper (Google, 2026) that dbv-specs-ops is built on: the marginal cost of adding features, refactoring, or deploying drops radically when the AI operates inside a structured, self-governed code factory with a low error rate. The CapEx of writing specs is an investment that pays continuous OpEx dividends.

Build docs developers (and LLMs) love