vc-generate-spec

vc-generate-spec is a skill for Claude Code from withkynam/vibecode-pro-max-kit. It costs 43 tokens per session (1,274 once invoked), scanned A, original, MIT.

A guide for creating a product-discovery specification, a plain-language document describing what should be built and why.

In plain words
What is it for?
Use it to write or update a SPEC for a non-trivial product task, including the program-level requirements for a multi-phase project.
Why use it?
It turns research findings and user intent into a reviewable agreement before anyone chooses a technical approach or starts planning implementation.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Codex.

About the project

vibecode-pro-max-kit is a set of instructions, agents, skills, hooks, and settings that gives AI coding agents a plan-first software development workflow. It is designed for developers, product owners, and other builders using agents such as Claude Code, Codex, Cursor, Windsurf, or Copilot across different technology stacks. The catalogue entries are the kit's own workflow components.

withkynam/vibecode-pro-max-kit · 1,114 stars · on GitHub

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/withkynam/vibecode-pro-max-kit/vc-generate-spec
Any agent
npx skills add withkynam/vibecode-pro-max-kit --skill vc-generate-spec
Clone the repo
git clone --depth 1 https://github.com/withkynam/vibecode-pro-max-kit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for vc-generate-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/withkynam/vibecode-pro-max-kit/vc-generate-spec.svg)](https://agentmods.dev/skills/withkynam/vibecode-pro-max-kit/vc-generate-spec)
Your own site
<a href="https://agentmods.dev/skills/withkynam/vibecode-pro-max-kit/vc-generate-spec"><img src="https://agentmods.dev/badge/skills/withkynam/vibecode-pro-max-kit/vc-generate-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,274 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 5.1 $0.00043 $0.01274
Opus 5 $0.00022 $0.00637
Sonnet 5 $0.00009 $0.00255
Haiku 4.5 $0.00004 $0.00127

Measured 6d ago against content hash be89c067223a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

vc-generate-spec 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 6d 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.

.claude/skills/vc-generate-spec/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate SPEC

Output style: Follow process/development-protocols/communication-standards.md — answer-first, plain language, no unexplained jargon, TL;DR on long responses.

Use this skill to produce the authoritative product-discovery SPEC artifact for a task — a plain-language requirements document written for user review, not for an engineer.

A SPEC captures what the user wants and why so the user can read it, recognize their own intent, and confirm "yes, build that" before any approach or code is chosen. It is the bridge between RESEARCH (the facts) and INNOVATE (the how). PLAN cannot start until a SPEC exists for non-trivial work.

SPEC consumes: RESEARCH findings + the user's stated intent/brainstorm. It does NOT consume a chosen approach or a Decision Summary — no approach exists yet at SPEC time.

Normal output is one SPEC file: {slug}_SPEC_{dd-mm-yy}.md.

For a phase program, the program-level (umbrella) SPEC is written once during the outer loop and governs every inner phase. Use templates/program-spec-template.md for that case. The inner loop never writes a SPEC.

Workflow

  1. Read references/spec-contract.md for the full section-by-section writing rules.
  2. Run date +%d-%m-%y before choosing the filename.
  3. Confirm the inputs are present: RESEARCH findings + the user's stated intent. If neither is present, emit SPEC_INTENT_BLOCKED instead of writing.
  4. Read process/context/all-context.md first, then load the relevant context group. When the work touches testing/verification, read process/context/tests/all-tests.md so acceptance-criteria scenarios are grounded in the real test-context chain.
  5. Save the SPEC inside the task folder alongside the plan: process/features/{feature}/active/{slug}_{date}/{slug}_SPEC_{date}.md (or process/general-plans/active/{slug}_{date}/{slug}_SPEC_{date}.md). For a phase program, the umbrella task folder holds {program-slug}_SPEC_{date}.md. Per task-folder artefact colocation, never write to the deprecated sibling reports/ or references/ dirs.
  6. Write the SPEC sections in canonical order (see references/spec-contract.md):
    • ## Summary
    • ## User Stories / Jobs To Be Done
    • ## What The User Wants (Behavioral Outcomes)
    • ## Flow / State Diagram (ASCII)
    • ## Acceptance Criteria (Testable Outcomes) — each criterion carries proven by: + strategy:
    • ## Out Of Scope
    • ## Constraints
    • ## Open Questions
    • ## Background / Research Findings
  7. Keep the document oriented for user review: plain language, no file paths, no library names, no schema or code. Anything engineer-only moves to Background or a later phase.
  8. Each acceptance criterion MUST be provable by comprehensive tests, with a fully-automated E2E/integration gate wherever the behavior is automatable. Agent-Probe / Known-Gap stand only as an explicitly-justified residual. Vacuous-green is banned.
  9. If ## Open Questions is non-empty at finalize (interactive session): emit SPEC_INTENT_BLOCKED and stop. Under /goal: record each as a backlog note and continue.
  10. Once Open Questions is empty/"None" (or backlogged under /goal): save the file and the agent emits PHASE_COMPLETE: SPEC.

Read the full file on GitHub · 72 lines

Files

What ships with it

2 files 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. 6d ago First seen · 72 lines · 43 tokens per session scan A be89c067223a

Subscribe to this mod's changes

vc-generate-spec is a skill published in the GitHub repository withkynam/vibecode-pro-max-kit (1,114 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,274 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 2026-08-30.

Related

Other skills, from other repositories

implement

End-to-end workflow for taking MCP work items from backlog to merged PR. Handles git branching, schema-driven planning, implementation, independent review, and PR creation. Composes spec-quality, review-quality, and schema-workflow skills into a single pipeline. Use when a user says "implement this", "work on this…

jpicklyk/task-orchestrator · 101 tokens

session-retrospective

Analyzes the current implementation run — evaluates schema effectiveness, delegation alignment, note quality, and plan-to-execution fit. Captures cross-session trends and proposes improvements when patterns repeat. Use after implementation runs, or when user says 'retrospective', 'session review', 'what did we learn'…

jpicklyk/task-orchestrator · 107 tokens

adopt-project-scope

Migrates an already-populated, unscoped Task Orchestrator database in place to the project-scoping convention — creates a project anchor root, re-parents existing work trees under it, and writes rootId back to config.yaml. Use when a user says: adopt project scope, migrate this database to project scoping, make this…

jpicklyk/task-orchestrator · 99 tokens

dependency-manager

Visualizes, creates, and diagnoses dependencies between MCP work items. Use when a user says: what blocks this, add a dependency, show dependency graph, why can't this start, link these items, unblock this, remove dependency, or show blockers.

jpicklyk/task-orchestrator · 53 tokens

manage-schemas

Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…

jpicklyk/task-orchestrator · 212 tokens

quick-start

Interactive onboarding for the MCP Task Orchestrator. Detects empty or populated workspaces and walks through how plan mode, persistent tracking, and the MCP work together. Use when a user says "get started", "how do I use this", "quick start", "first time setup", "onboard me", "what can this MCP do", or "help me…

jpicklyk/task-orchestrator · 82 tokens