Do I need an API key to connect Claude Code to Scriptonia?

No. npx scriptonia login opens a browser sign-in and stores credentials locally. The Claude Code skill and AGENTS.md section are installed in the same step; you never see or paste a key.

Does this work with Codex, Cursor, or OpenClaw too?

Yes. Those agents read the same AGENTS.md contract. MCP-native agents can connect directly with npx -y scriptonia mcp. Claude Code additionally gets a dedicated skill.

What changes in how Claude Code behaves?

Before building user-facing changes it runs scriptonia plan, executes the resulting PLAN.md exactly, respects its Non-goals, stops on any UNRESOLVED constraint, and cites signal ids in the PR description.

How to give Claude Code a product brain in 5 minutes

To give Claude Code a product brain, install Scriptonia with npx scriptonia login, feed it customer signal with scriptonia add, and generate plans with scriptonia plan. A skill and AGENTS.md are wired automatically, so Claude Code grounds its work in real customer signal from then on.

By the end of this page, Claude Code will know what your customers asked for, which decisions your team already made, and exactly where the fence around a feature sits. Five minutes, four commands, no configuration files.

Step 1 — Install and sign in (60 seconds)

$ npx scriptonia login
 
  Opening your browser to sign in…
  ✓ Signed in  (project created, sample data included)
  ✓ Agent wired — skill + AGENTS.md know about `scriptonia plan`

That second checkmark is the integration. A skill lands in ~/.claude/skills/scriptonia/ and your repo's AGENTS.md gets a managed section. Claude Code reads both automatically.

Step 2 — Feed it customer signal (free, always)

$ scriptonia add slack-thread.txt call-with-acme.vtt notes.md
$ scriptonia add "Compliance can't use the audit log without per-actor filtering"

Tickets, transcripts, pasted rants. Everything is embedded and kept traceable to its source. Adding signal never costs credits on any plan, because a starving brain helps nobody.

Step 3 — Turn an issue into a plan (~15 seconds)

$ scriptonia plan "filter the audit log by actor"
 
  ✓ Plan filter-audit-log-by-actor v1 → PLAN.md
  5 cited signal(s), 1 unresolved contradiction(s)

PLAN.md arrives with cited evidence, acceptance criteria, real file paths from a scan of your repo, a Non-goals fence, and, in this example, a ⚠ UNRESOLVED gate because the issue conflicts with a recorded roadmap decision. Claude Code is instructed to stop at that gate until a human clears it.

Step 4 — Let Claude Code ship it

$ scriptonia comment plan/filter-audit-log-by-actor "Approved — override the April call."
$ claude "execute PLAN.md"

The approval flips the gate to RESOLVED, the plan regenerates as v2, and Claude Code builds exactly what the plan says: one filter, not five, with the customer's ticket cited in the PR.

Why this beats pasting context into a prompt

A pasted prompt is one voice, once, and it forgets what you decided last quarter. Agent product memory retrieves across everything you've ever added, checks the decision corpus, and produces the same grounded plan for any agent, every time. The setup you just did is permanent; from now on the loop is just add → plan → build.