Skip to content
The method

Work with coding agents and keep the record straight.

Each step is a tool from the Agent Workbench, and each tool does only what it does today. The numbers at the end come from the Lab write-ups, not from this page.

  1. 01

    Keep the backlog a schema

    roadkeep owns the writes to the roadmap, the changelog and the rationale. An agent files and ships work through a command that checks the line's shape at insertion, and the Claude Code plugin refuses the hand-edit, so the backlog cannot drift when someone is in a hurry.

  2. 02

    See what every project owes

    roadkeep-gui finds every governed checkout on the machine and shows what each has shipped and still owes. It files or ships a line through the roadkeep command, and hands a task to Claude Code as a session it starts, claims and shows while it works.

  3. 03

    Let the diff write the commit

    commitclerk reads the staged diff, asks an LLM for a Conventional Commits message, shows it to you and commits only once you agree.

  4. 04

    Test what was observed

    winwright drives the Windows app from a test and reports four verdicts, so a check that could not run is never filed as one that passed.

  5. 05

    Give the agent a domain it can check

    polyweave declares what a 3D asset must satisfy and searches for parameters that do, asserting every render; Piano's plugin writes, checks and keeps scores before the app plays them. Same discipline: a declared target, checked, recorded.

  6. 06

    Keep the usage in view

    Claude Code Tray puts the rate-limit percentage in the tray, read from the session files already on disk.

Measured, not claimed

What the records say

One developer's sessions, attributed from transcripts and git history. Each figure links the sentence it is quoted from.

Time Study
530 h

of attributed time, across 556 sessions in 59 days

“59 calendar days, 556 sessions, 31 projects, 530 hours of attributed time” — source
Time Study
11.2%

of active time went to authoring the feature

“feature authoring is 11.2%, less than half the expected share” — source
Time Study
27.3%

went to writing and running tests

“Tests (writing + running) | 124 | 27.3%” — source
Usage Simulator
1,864

tasks measured, over 79,377 requests in 32 active days

“The current snapshot covers 1,864 tasks and 79,377 requests over 32 active days.” — source
Usage Simulator
$777

for the most expensive five-hour window on record, at list prices

“the most expensive five-hour window on record cost $777 at list prices with work uninterrupted” — source