OneShot

Receipt-verified build packs

Build packs your coding agent executes.

Complete PRD, architecture, task graph, and acceptance tests — feed one to your own agent and it builds the complex, universal part of your product. Every listing carries a public execution receipt proving the build works before you spend anything.

  1. 01

    Buy the pack

    A complete PRD, architecture decisions, task graph, acceptance tests, scaffold, and prompts — every decision pre-made.

  2. 02

    Feed it to your agent

    Claude Code or Cursor builds inside the pinned scaffold, task by task, with no context beyond the pack.

  3. 03

    Verify

    Run the pack's own acceptance script and compare against the published receipt. The destination is proven, not promised.

Catalog

How receipts work

Before a pack is listed, our verification harness executes it the same way you will — a fresh agent, a clean scaffold, the pinned model. The receipt is the machine-generated record of those runs, published in full.

Pass rate, as M of N
Our harness runs each pack from a clean scaffold N times on the pinned model and publishes exactly how many runs passed. Agent builds are stochastic — a pack that passes 4 of 5 is listed as 4 of 5, never as "always one-shots."
Everything pinned
The exact model id and exact dependency versions the runs used are locked into the receipt. What was verified is what you build with.
Measured cost
Token counts and wall time in the receipt are per-run means from real runs. The token figure on a catalog card is an estimate and is labeled as one.
Tamper disclosure
The receipt lists every scaffold file the building agent modified or deleted. An empty list means built pristine. Modifications are disclosed, not hidden.
Pending means pending
A pack without a completed verification run says "Verification pending" and publishes no numbers. We never invent them.