ZeNorm
Try it free→

Ask. Answer. Build.

Describe a feature. ZeNorm asks the hard questions. You get an agent-ready spec.

Start your first spec→How it works
Works with
+ every major agent
Live 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
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 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.
How 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, runs your agent, and gates every result on typecheck + tests. Or run a single spec yourself with /zenorm Z-123.
ZeNorm 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
→ branch zenorm/checkout-flow-2605271430
✓ 4 tasks implemented
Hands-free execution

Start it once. Come back to branches.

zenorm work picks up ready tasks, runs your coding agent, and checks every result against typecheck, lint, and tests — one command, no babysitting.

  1. ⟁
    Pick up
    Watches for ready tasks. Picks up the oldest one and locks it so nothing else touches it.
  2. ▸
    Implement
    Runs your agent with full spec context — every constraint, decision, and edge case baked in.
  3. ⊘
    Verify
    Typecheck, lint, tests. Passes the gate or retries. Escalates only if it has to.
  4. ✓
    Ship
    Branch 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→
Pricing

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
  • Enough usage for your first specs
  • Public CLI
  • Personal workspace
Try it free→
No credit card required
Individual
$26.99per month

No per-spec limits, predictable cost. Ship faster solo.

  • $26.99 of spec generation + refinement monthly
  • No per-spec limits — one usage allowance
  • 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?
Run zenorm work --agent claude and it picks up tasks automatically — no interaction needed. Or run a single spec in your agent directly: in Claude Code that's /zenorm Z-123. Both paths load full spec context. 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.
Can specs run without me?
That's the default. zenorm work picks up ready tasks, runs your coding agent, and verifies every result against typecheck + lint + tests. Start it once and come back to branches. Running a single spec manually with /zenorm Z-123 is there when you want direct control.
How does usage work?
Each paid plan includes a monthly usage allowance covering spec generation and refinement. You can see the meter, and it hard-stops at the limit instead of overcharging. Running specs in your coding agent (Claude Code, Cursor, OpenCode, etc.) is billed by that agent's provider, not ZeNorm. Starter includes free usage so you can see how ZeNorm fits your workflow before upgrading.

Ask. Answer. Build.

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

Start your first spec→See how it works