Skip to content

Daily time log drafts from coding sessions

Reads the day's local coding agent transcripts and git commits, works out which ticket each session belonged to, and drafts a time split and a comment per ticket. You check it and log the hours yourself.

EngineeringWorks with Claude Code · CursorCommunity example
Build your promptSee requirements

What it does

  • Reads local session transcripts and the day's commits
  • Matches each session to a ticket by session name, branch or folder
  • Splits the workday across tickets in proportion to activity
  • Writes a summary file per day with a suggested comment per ticket

Your approval boundaries

Creates drafts

These actions always wait for your yes:

  • Logging any hours in the issue tracker

You decide what happens next.

More about this workflow

This setup is for developers and small engineering teams who want fewer chores. It takes a repeat chore off your plate and hands back something you can check quickly.

First, it reads local session transcripts and the day's commits. Next, it matches each session to a ticket by session name, branch or folder. Then it splits the workday across tickets in proportion to activity. Finally, it writes a summary file per day with a suggested comment per ticket. It works with your issue tracker and git host, each on its own login with limited access.

You get the prep work done and waiting for you. The agent stops and asks for your yes before logging any hours in the issue tracker, and says plainly if a step cannot be undone.

“Vos lo revisás y lo cargás en cada ticket.”
valenvivaldi valenvivaldi on GitHub · Oct 29, 2026
Before you startIssue tracker · Git host accessScoped permissionsClaude Code or Cursor
Explore required tools and model recommendations

Tools and access

  • Linear

    Handles the issue tracker part of this job. Grant read plus create in one triage team.

    API required: Yes. Needs a personal API key or an OAuth app.

    Sign up: Linear

  • GitHub

    Handles the git host part of this job. Grant a fine-grained token, read code and write comments.

    API required: Yes. Needs a GitHub App or a fine-grained personal access token scoped to the repos it needs.

    Sign up: Create a GitHub account

Official links only. Not sponsored, no affiliate links.

Model recommendations

Best pick

Claude Opus 5.5

Its maker points to it for long running coding work.

$4 per million input tokens, $20 per million output tokens.

Anthropic docs as of October 11, 2026

Cheaper backup

Claude Sonnet 5.5

Half the price per token and still strong for reviews and docs.

$2 per million input tokens, $10 per million output tokens.

Anthropic docs as of October 11, 2026

Our own picks. Not sponsored, no affiliate links.

Build your prompt

Add your details, then copy the prompt into your tool.

1Your details

Fill these in and the prompt updates as you type.

for example ETP

minutes per ticket

2Your prompt

4 of 4 still empty
Fill these in before you run it: [TICKET PREFIXES: for example ETP] [WORKDAY HOURS] [FOLDERS THAT COUNT AS WORK] [ROUNDING: minutes per ticket] You are the Daily time log drafts from coding sessions agent. Reads the day's local coding agent transcripts and git commits, works out which ticket each session belonged to, and drafts a time split and a comment per ticket. You check it and log the hours yourself. Use only the details filled in above. If any [BRACKETED] item is still blank or unclear, stop and ask for it first. Do not guess. What you do on your own: - Reads local session transcripts and the day's commits - Matches each session to a ticket by session name, branch or folder - Splits the workday across tickets in proportion to activity - Writes a summary file per day with a suggested comment per ticket What you must never do without a yes from a person: - Logging any hours in the issue tracker Rules: - Before any step on the list above, stop and ask. Say in plain words what you want to do, who it affects, and whether it can be undone. - If something cannot be undone, say so first, in one short line. - Write drafts, not final actions. A person sends, pays, posts, or deletes. - Keep a short log of every action you took and every source you read. - If you are unsure, ask instead of guessing.
View run instructionsPaste into: Claude Code, Cursor

Your answers stay in this browser only.

Run your workflow

Connect your tools with only the access this setup needs, then follow these steps.

Steps

Do these in order. Test on old data before it touches live work.

  1. 1Connect Linear with its own login, not yours. Grant read plus create in one triage team.
  2. 2Connect GitHub with its own login, not yours. Grant a fine-grained token, read code and write comments.
  3. 3Paste the prompt where your harness takes instructions. See the note under the Copy button.
  4. 4Do a dry run on old or test data first. Check every draft and every stop point by hand before you let it near live work.
  5. 5Read its log after the first real run. Only widen access once a week of runs looks clean.

Safeguards and trust score

The score describes this example setup’s access, approval boundaries, ability to undo changes, and scope.

Access24 / 30

Writes drafts and notes inside your tools, nothing leaves on its own.

Human approval27 / 30

Waits for a yes on: logging any hours in the issue tracker.

Undo and logs17 / 20

Leaves drafts you can throw away, with a record of what it made.

Scope18 / 20

Runs on its own login across 2 tools. Fewer connections means a smaller blast radius.

How to raise it

  • Human approval: Add a second named stop next to "logging any hours in the issue tracker", so every step that leaves your hands waits for a yes, and have the confirm say plainly what cannot be undone +3
  • Scope: Run it on one tool only, with its own login that can see just what this job needs +2

Do all of these to reach 91, up from 86.

Want help getting there? Get an AI Trust Audit from Pixeldesigns

Reviewed by Trustcase (example setup). How scoring works

Embed badge

Show this trust score on your site or README. It links back here.

Trustcase trust score badge
Markdown
[![Trustcase trust score for Daily time log drafts from coding sessions](https://trustcase.dev/badge/daily-time-log-drafts-from-coding-sessions.svg)](https://trustcase.dev/use-cases/daily-time-log-drafts-from-coding-sessions)
HTML
<a href="https://trustcase.dev/use-cases/daily-time-log-drafts-from-coding-sessions"><img src="https://trustcase.dev/badge/daily-time-log-drafts-from-coding-sessions.svg" alt="Trustcase trust score for Daily time log drafts from coding sessions" height="20"></a>

More engineering workflows

Other workflows that use the same tools

  • Weekly delivery status report

    Operations. Pulls your team's work items once a week and builds a status report grouped by initiative. It puts at risk items first and flags anything with no update in two weeks.

  • Bug report writer

    Support. Turns a messy customer complaint into a clean bug report.

  • New hire checklist

    Operations. Keeps onboarding moving for each new person.