ZeNorm
Try it free→

Spec-driven development, minus the spec-writing.

Describe the feature. ZeNorm asks the hard questions. Your agent gets a spec worth building.

Start your first spec→How it works
Works with
+ every major agent
ILive demo

See what a finished spec looks like

Four decisions take raw intent to goals, constraints, and agent-ready tasks. 30 seconds.

ZeNorm spec editor: an empty spec outline with Overview, Intent, Constraints, Acceptance, and Tasks sections, ready for the agent's first question
IIThe missing step

Great specs are discovered, not drafted.

Most agent failures start before code — vague intent, missing constraints, hidden edge cases. ZeNorm surfaces those gaps first.

What you said
> Add role-based access so
> admins can manage the team
Clear enough to start. Not enough to finish.
What ZeNorm found
✓ 5 roles scoped to org
✓ Invite flow + seat limits
✓ Owner-transfer safeguard
→ 4 agent tasks generated
Same idea. Agent-ready in minutes.
IIIHow it works

Describe it. Answer the hard questions. Run it.

Three steps from rough idea to reviewed, executable spec — you make the calls, your agent does the typing.

  1. 01
    step 01
    Start with what you know
    Describe the feature in plain language. ZeNorm connects to your repo — then asks the questions you didn't know to ask.
  2. 02
    step 02
    Answer the hard questions
    ZeNorm probes intent, constraints, and assumptions — the details that become bugs when nobody calls them out. A real spec, not a chat log.
  3. 03
    step 03
    Execute the whole spec
    Point zenorm work at your repo and it picks up tasks and runs your agent, which passes typecheck + tests before completing each one. Or run a single spec yourself with /zenorm Z-123.
IVZeNorm CLI

Wire up Claude Code in four commands.

Installing the skill adds a /zenorm Z-123-style command to Claude Code for running a spec directly. zenorm work runs specs hands-free.

# 1. install the CLI
$npm install -g @ze-norm/cli
# 2. sign in
$zenorm login
# 3. install the ZeNorm skill into Claude Code
$zenorm install-skills claude-code
# 4. run specs hands-free
$zenorm work --agent claude-code
# or invoke the skill to run one spec in Claude Code
$/zenorm Z-123
→ zenorm skill · loaded spec checkout-flow
→ agent implementing tasks
→ commit feat(checkout-flow): stripe handler
✓ 4 tasks implemented
VHands-free execution

Start it once. Come back to commits.

zenorm work picks up ready tasks and runs your coding agent, which passes typecheck, lint, and tests before completing each one — one command, no babysitting.

  1. 01
    Pick up
    Watches for ready tasks. Picks up the oldest one and locks it so nothing else touches it.
  2. 02
    Implement
    Runs your agent with full spec context — every constraint, decision, and edge case baked in.
  3. 03
    Verify
    Typecheck, lint, tests. Passes the gate or retries. Escalates only if it has to.
  4. 04
    Ship
    Commits ready for review. Moves on to the next task.
zenorm work
$zenorm work --agent claude
┌─────────────────────────────────────┐
│ zenorm work │
│ agent: claude · polling: 5s │
│ repo: acme/checkout-service │
└─────────────────────────────────────┘
── stripe-checkout ─────────────────────
◆ editing src/checkout/handler.ts
▸ pnpm typecheck && pnpm test
✓ task complete · 2m 14s
── cart-recovery ───────────────────────
○ reading src/cart/recovery.ts
◆ editing src/cart/recovery.ts
▸ pnpm typecheck && pnpm test
✓ task complete · 1m 48s
✓ 2/2 tasks complete · 4m 02s
Try it free→
VIPricing

Start free. Predictable after.

One plan for solo devs. Teams and orgs talk to us.

Starter
$0free

Try the full spec workflow free.

  • Spec authoring + /zenorm execution
  • Your first 10 specs free
  • Public CLI
  • Personal workspace
Try it free→
No credit card required
Individual
$27.99per month

Unlimited spec work, one flat price. Ship faster solo.

  • Unlimited spec generation + refinement
  • No per-spec limits, no metering
  • Personal workspace
  • One flat price — no per-run or overage charges
Start free, upgrade later→
Team
Contact usper org

Shared specs, shared repos, pooled usage. Built around how your team ships.

  • Everything in Individual
  • Org workspaces with role-based access
  • Shared repository connections
  • Pooled usage and unified billing
  • Priority support
Talk to us→
VIIQuestions

Common questions

What people ask before signing up.

How is this different from just using Claude Code / Cursor?
Those are coding agents — they execute fast but only know what you tell them in the moment. ZeNorm sits before them. It interrogates your intent, grounds it in your codebase, and produces a spec that reduces what your agent has to infer.
How do specs get executed?
Two ways. Hands-free: zenorm work --agent claude picks up ready tasks and hands each one to your coding agent with full spec context — the agent runs typecheck, lint, and tests before marking a task complete. Direct: run a single spec in your agent yourself — in Claude Code that's /zenorm Z-123. Either way the spec is the contract; the agent is the executor.
Can I review the spec before anything runs?
Yes — that's the point. The spec is visible, editable, and yours. Nothing reaches your coding agent until you're satisfied with it.
What if the agent gets something wrong?
That's why the spec exists. When the output doesn't match, you can see which constraint, assumption, or edge case needs tightening — not just that something looks off. Fix the spec, then re-run with clearer context.
Why not just write a better prompt?
Prompts expire when the session ends. A spec persists across sessions, agents, and teammates. And a spec that's been interrogated — where someone asked 'what about timeouts?' and 'what happens on failure?' — produces dramatically better agent output than a prompt ever will.
What happens to my code?
ZeNorm reads your code only to ground your specs. You connect GitHub yourself, and during a session the agent reads from a temporary clone that's deleted when the session ends — ZeNorm never stores a copy of your repository, and never writes to it. Specs and everything derived from them live in your workspace, scoped to your org.
How does usage work?
The Individual plan is unlimited — one flat monthly price covers all your spec generation and refinement, with no metering and no per-run or overage charges. Starter is free — no credit card — and includes your first 10 specs, enough to see how ZeNorm fits your workflow before upgrading. Running specs in your coding agent (Claude Code, Cursor, OpenCode, etc.) is billed by that agent's provider, not ZeNorm.

Your next feature, minus the spec-writing.

Free to start. No credit card. Just answer the hard questions.

Start your first spec→See how it works