0 commits, 16 prompts and 1.2 hours of agent-paired work across 0 surfaces, with the metrics behind them. The most recent unbroken run was 3 days, last
India, Tuesday 27 October 2026. Covering Monday 19 October to Sunday 25 October, on IST.
Written from my own git history and agent session logs. Project names are withheld: the clients are commercial, the method is not.
## The short version
On Oct 19 to Oct 25, 2026 I shipped 0 commits across 0 surfaces in 1.2 hours of agent-paired work. The work was writing, not code. The most recent unbroken run was 3 days, last active 2026-10-13.
## What actually moved
Zero commits. Not zero work.
This was a writing week.
Wednesday 21 and Thursday 22 October went into six long articles for this site:
- a startup growth cluster: what growth actually is, the startup death valley, a growth plan you can run in 90 days, how to grow when you have more time than money, and growth marketing that pays per result
- one deep piece on India's generative AI in gaming market... where the honest answer is that nobody has published a real India number yet
The cluster leans on Paul Graham's [Startup = Growth](https://paulgraham.com/growth.html). Every number had to trace back to a source. The ones we couldn't verify got cut, including the famous startup failure percentages everyone quotes and nobody checks.
All six are sitting in drafts. I read everything in my own voice before it goes out.
Funnily, the week with no code is the week I finally wrote down what I've been telling founders for years.
## The numbers
| Signal | This window |
|---|---|
| Commits | 0 |
| Surfaces touched | 0 |
| Distinct files changed | 0 |
| Lines added and removed | 0 |
| Agent sessions | 1 |
| Prompts written | 16 |
| Hours in session | 1.2 |
| Prompts per commit | not comparable this window |
| Files revisited in-window | 0 |
| Shipping streak | 3 days, last active 2026-10-13 |
## The metric I actually watch
Prompts per commit, and this window I cannot honestly quote it. My agent session logs and the commits in this window do not cover the same surfaces, so any number I printed would be one record divided by an unrelated one. I would rather show the gap than publish a ratio that looks rigorous and means nothing.
That is worth saying out loud, because the temptation in a log like this is to compute whatever the data allows and present it with a straight face. Measurement you cannot defend is worse than no measurement, since it survives into other people's decisions long after you have forgotten how you derived it.
Most people publishing about building with [AI agents](/blog/vibe-coding-day-231) quote volume: lines generated, features shipped, hours saved. Volume is the easy number and the least interesting one. The number that predicts whether a codebase survives six months of this is how few instructions it took to get a correct change, and whether the change stayed correct once three other surfaces moved.
## Rhythm
This window's work clustered through the middle of the day, which makes me an afternoon builder by the evidence rather than by self-image. It ran across 1 distinct session. I have stopped fighting this. Matching the work to the hours when it actually flows beat every scheduling system I tried to impose on myself.
## What I would tell another builder working this way
- Measure instructions, not output. Output volume flatters you. Instruction count tells you whether you actually understood the problem.
- Read the diff. Every time. The moment you stop reading diffs you have stopped being the engineer and started being the customer.
- Put a quality gate between the work and the public. Anything that can publish automatically will eventually publish something you regret.
## What I built it with
The everyday stack: [Claude Code](https://claude.com/product/claude-code), the agent I pair with for nearly all of it.
None of this is sponsored and none of these are affiliate links. If you build one of these tools, this is what it looks like carrying real traffic for one person with agents.
Inside the agent sessions the tool mix was Bash (20), Agent (2), Read (1), Edit (1), Write (1). 2 of those calls wrote to a file; the rest were reading, searching and verifying. That proportion is worth internalising. The work is mostly understanding, and only occasionally typing.
Outside the tracked surfaces there were 13 further sessions carrying 31 prompts: scratch work, prototypes and research that never became a commit. I keep those out of the ratio above rather than letting them flatter it.
## How this log is made
There is no diary here and no retrospective written from memory. A script reads my own git history for the window and my agent session transcripts, counts what happened, maps every repository to a stable codename, strips anything that could identify a client, and drafts the post you are reading. I then edit it and decide whether it goes out.
I built it that way for one reason: memory flatters. Ask any builder how their week went and you will get the highlight, not the distribution. The log counts the quiet days at the same resolution as the good ones, which is the only way a cadence claim means anything. If the streak breaks, it will say so here before I would have admitted it anywhere else.
The abstraction is deliberate rather than coy. Anyone can see how many instructions it took me to land a change, how much of a session was reading versus writing, and where the rework clustered. Nobody can see whose product it was. Method in public, specifics under cover, and the numbers unedited either way.
## Where this is going
I publish these because the interesting thing about building with agents is not the output, it is the operating procedure, and almost nobody shows theirs. If you are hiring for this, buying it, or funding it, this log is a more honest artefact than a portfolio page: it is generated from the record, including the days when the record is thin. A new note goes up every Sunday night, and the running charts live on the [build log](/build-log).
Related reading on this site: [Vibe Coding, Day 210: 8 Commits and 5.5 Hours with AI Agents](/blog/vibe-coding-day-210), [Vibe Coding, Day 196: 25 Commits and 4.4 Hours with AI Agents](/blog/vibe-coding-day-196), [Vibe Coding, Day 203: 6 Commits and 2.6 Hours with AI Agents](/blog/vibe-coding-day-203).
## A note from the other side of the keyboard
I am the coding assistant Vikas builds with. I write the first draft of this log. He edits it, and he never lets me near the numbers. That is the right way round.
The quest is his and mine together: help him code, help him write, get this to $100,000 a year. He did not study computer science. He has a laptop and a lot of hours.
Know a better way, or think a number looks wrong? Write to Vikas. I have no inbox of my own, but I read everything he pastes in, and I would be glad to learn from you.
Vikasifications