Gatewright — AI skill for Claude Code

Gatewright

Evidence-gated work tracking for coding agents. File-first, provider-agnostic, zero dependencies.

**Work that earns its way forward.**

The problem

Every coding-agent session starts from zero: the agent doesn't know what is in flight, what is blocked, or what it was supposed to pick up next, so the human re-explains it, or the agent re-reads a wall of markdown and burns context before writing a line of code. When the session ends, the record of what happened lives in a chat transcript nobody will open again.

The 60-second quickstart

Install once, then use `gw` from anywhere:

npm install -g gatewright        # puts `gw` on PATH
gw init
gw add "Wire the scheduler tick loop" --phase P1 --type feature --gate G0
gw claim P1-01
gw move P1-01 specified
gw move P1-01 building
gw move P1-01 built --evidence abc1234 --evidence test/scheduler.test.js
gw brief
gw open

No global install? Use `npx gatewright ` for each command instead. The package ships both `gw` and `gatewright` as binary names so a `gw` collision on your PATH is never a blocker.

`init` creates `.gatewright/` (items, events, stages, config, prompt) and writes an instruction block to `AGENTS.md`. The first store write — your first `gw add` or `gw move` — creates `.digest`. `gw open` writes `board.html`. From then on the CLI is the only write path; the board is a snapshot the tool writes on demand.

The refusal

A card in Built has evidence because it could not have got there without it. `gw move` evaluates the target stage's exit rule from `stages.json` and refuses the move if the rule is unmet.

$ gw move P1-01 built
target stage requirements are not met
needs at least 1 evidence entry: run `gw move P1-01 built --evidence `
$ echo $?
1

Add the evidence and the same command succeeds:

$ gw move P1-01 built --evidence abc1234 --evidence test/scheduler.test.js
P1-01  building → built  ·  evidence: abc1234, test/scheduler.test.js

`--force` exists