Technical resources
Our standards, in the open.
The conventions, guides and templates we apply on every project. Click a resource to read it in full.
Chasing a specific production error? Browse the answers.
| Resource | Description | Type | Status | Updated |
|---|---|---|---|---|
| What a fleet of agents actually costs | Seven weeks of development measured in production: 279 agent runs, 41.9 agent hours, 1.16 billion input tokens, for 73 merged PRs. Raw data, open to export. | measurement | active | Aug 2026 |
| Resource | Description | Type | Status | Updated |
|---|---|---|---|---|
| LLM API cost calculator | Enter your token ratio, your server cost, your exchange rate: compare Claude, GPT-5 and Gemini against a self-hosted GPU server, live. | calculator | active | Aug 2026 |
| Resource | Description | Type | Status | Updated |
|---|---|---|---|---|
| design.md | UI conventions shared across all our projects: stack, primitives, custom patterns, baseline accessibility, copy. | standard | active | Jun 2026 |
| Resource | Description | Type | Status | Updated |
|---|---|---|---|---|
| The Claude Code setup we run | Our actual configuration: the three rule files, the hooks that block, the 5 agents, the skills, session continuity and memory. Not a tutorial, the config we run. | guide | active | Sep 2026 |
| Agent John, from client request to shipped PR | How a plain-language client request becomes a ticket, a verified code analysis, then a pull request, across three agents with strictly separated permissions. | case study | active | Aug 2026 |
| Back-office functional spec | An exhaustive functional specification for internal tools: every process, every screen field, every formula and the data model, defined before a line of code. | guide | active | Jul 2026 |