ZeNorm
Try it free→

Prompts expire. Specs ship.

Describe a feature. ZeNorm interrogates your intent, grounds it in your codebase, and hands your agent a spec — not a guess.

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

See what a finished spec looks like

From raw intent to goals, constraints, and agent-ready tasks. 30 seconds.

ZeNorm spec editor: an answered question and a pending agent question alongside goals and constraints
The 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 so your agent doesn't have to guess.

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
Every edge case surfaced before code.
How it works

Describe it. Answer the hard questions. Run it.

AI can write code. It can't read your mind.

  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
    Invoke the ZeNorm skill in Claude Code — e.g. /zenorm Z-123. Every task runs with constraints, decisions, and edge cases already baked in.
ZeNorm CLI

Three commands to wire up Claude Code.

Install once, then run any spec — tasks execute in dependency order with full context.

# 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 a spec in Claude Code
$/zenorm Z-123
→ loaded spec · checkout-flow
→ implementing tasks
→ branch zenorm/checkout-flow-2605271430
✓ 4 tasks implemented
Pricing

Start free. Predictable after.

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

Starter
$0free

Try the full spec workflow. No credit card.

  • 3 specs per month
  • Spec authoring + /zenorm execution
  • Public CLI
  • Personal workspace
Try it free→
No credit card required
Individual
$30per month

Unlimited specs, predictable cost. Ship faster solo.

  • Unlimited specs and refinement passes
  • Stripe billing + self-serve portal
  • Personal workspace
  • Hard stop at limit — no surprise 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→
Questions

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 I execute a spec's tasks?
Install the ZeNorm skill with zenorm install-skills, then run a spec in your agent — in Claude Code that's /zenorm Z-123. The skill loads the spec context and implements the tasks. You can also pull spec context into any agent with zenorm pull. The spec is the contract; the agent is the executor.
Do I lose control?
No. The spec is visible, editable, and yours. You review it before anything runs. Nothing reaches your agent until you're satisfied with the spec.
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.
How does usage work?
Starter gives you 3 specs per month — enough to see if ZeNorm fits your workflow. Individual is unlimited specs and refinement for $30/mo with a hard stop, no surprise charges. Running specs in your coding agent (Claude Code, Cursor, OpenCode, etc.) is billed by that agent's provider, not ZeNorm.

Describe it. Decide it. Ship it.

Free to start. No credit card. Your next feature starts with the right questions.

Start your first spec→See how it works