spec-driven-vibe-coding

A workflow for turning vague software ideas or changes into written requirements, plans, tests, and review steps before AI-assisted coding begins.

In plain words
What is it for?
Use it for product ideas, features, design or behavior changes, bug fixes, refactors, prompt changes, and AI pipelines. It also defines a lighter process for disposable prototypes.
Why use it?
It reduces invented requirements, drifting implementations, and changes that are difficult to review or maintain.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/shmtulq-cloud/spec-driven-vibe-coding/skill
Any agent
npx skills add shmtulq-cloud/spec-driven-vibe-coding --skill skill
Clone the repo
git clone --depth 1 https://github.com/shmtulq-cloud/spec-driven-vibe-coding

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.01342
Opus 5 $0.00024 $0.00671
Sonnet 5 $0.00010 $0.00268
Haiku 4.5 $0.00005 $0.00134

Measured 2d ago against content hash 4e742acfe14b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-driven-vibe-coding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-Driven Vibe Coding

Use this skill when AI-assisted coding needs to produce maintainable Web/App product work rather than a throwaway demo.

Core idea

Treat AI coding as specification execution, not prompt improvisation. Vibe coding is useful for exploration, taste-making, and rapid option discovery. Production implementation should be spec-bound, testable, and reviewable.

The human role shifts from typing every line to orchestrating and validating: define intent, constrain scope, review architecture, verify correctness, and own what gets merged.

When to use

Use this for product ideas, new features, UX changes, behavior changes, brownfield refactors, bugfixes, prompt changes, agent workflows, structured generation, extraction/classification pipelines, and any work where AI may drift, invent requirements, or produce unreviewable changes.

Keep it lightweight for tiny changes. Still capture outcome, scope, acceptance criteria, implementation notes, and verification.

If the user explicitly asks for a disposable prototype, acknowledge the tradeoff and use only a short intent note plus a verification check.

Hard gates

Do not implement before there is a clear spec or approved design, unless the work is explicitly disposable.

Do not write production code for behavior changes before defining how the behavior will be verified.

Do not silently expand scope. If codebase reality conflicts with the spec, stop and propose a spec update.

Keep specs alive. If implementation changes behavior, constraints, APIs, architecture, or rollout assumptions, update the spec immediately.

Do not claim done, fixed, or passing without fresh evidence.

Coordinator / executor windows

For non-trivial implementation, treat the current conversation as the coordinator by default. The coordinator writes specs, plans, context packets, handoff prompts, audits, and acceptance decisions. It should not directly finish module work unless the task is tiny or the user explicitly asks to implement in this window.

Read the full file on GitHub · 129 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 129 lines · 49 tokens per session scan A 4e742acfe14b

Subscribe to this mod's changes

spec-driven-vibe-coding is a skill published in the GitHub repository shmtulq-cloud/spec-driven-vibe-coding (2 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,342 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens