Skip to content

Coding agent session journal

Writes one note a day on what your coding agent sessions did, decided and learned, then rolls the week into a review. It reads transcripts already on disk and only runs when you ask.

EngineeringWorks with Claude Code · CursorCommunity example
Build your promptSee requirements

What it does

  • Lists the sessions active that day from local transcripts
  • Drops quick lookups not worth an entry
  • Writes a day note with did, decided and learned per project
  • Rolls the week into highlights, wins and open threads

Your approval boundaries

Read only

Reads connected data. It does not send messages or change records.

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 lists the sessions active that day from local transcripts. Next, it drops quick lookups not worth an entry. Then it writes a day note with did, decided and learned per project. Finally, it rolls the week into highlights, wins and open threads. It works with your docs, each on its own login with limited access.

You get the finished work, ready to read. It only reads, so nothing is sent, changed or paid for. You decide what to do with it.

“It runs only when you ask”
chrisvaillancourt chrisvaillancourt on GitHub · Oct 16, 2026
Before you startDocs accessRead-only permissionsClaude Code or Cursor
Explore required tools and model recommendations

Tools and access

  • Google Docs

    Handles the docs part of this job. Grant one folder, create and edit only.

    API required: Yes. Needs a Google Cloud OAuth app with the Docs API turned on.

    Sign up: Google Workspace

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.

e.g. personal

what counts as work

2Your prompt

4 of 4 still empty
Fill these in before you run it: [JOURNAL FOLDER] [PROJECTS TO EXCLUDE: e.g. personal] [SCOPE: what counts as work] [WEEK START DAY] You are the Coding agent session journal agent. Writes one note a day on what your coding agent sessions did, decided and learned, then rolls the week into a review. It reads transcripts already on disk and only runs when you ask. 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: - Lists the sessions active that day from local transcripts - Drops quick lookups not worth an entry - Writes a day note with did, decided and learned per project - Rolls the week into highlights, wins and open threads What you must never do without a yes from a person: - Anything that writes, sends, or spends. This job only reads. 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 Google Docs with its own login, not yours. Grant one folder, create and edit only.
  2. 2Paste the prompt where your harness takes instructions. See the note under the Copy button.
  3. 3Do 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.
  4. 4Read 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.

Access30 / 30

Read only. It never writes, sends or spends.

Human approval30 / 30

Nothing to approve, it only reads.

Undo and logs20 / 20

No changes to undo. Reads can be logged.

Scope20 / 20

Runs on its own login across 1 tool. Fewer connections means a smaller blast radius.

How to raise it

Nothing major to fix. One polish tip: show a short daily log of what it read, so you can spot it reaching for anything new.

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 Coding agent session journal](https://trustcase.dev/badge/coding-agent-session-journal.svg)](https://trustcase.dev/use-cases/coding-agent-session-journal)
HTML
<a href="https://trustcase.dev/use-cases/coding-agent-session-journal"><img src="https://trustcase.dev/badge/coding-agent-session-journal.svg" alt="Trustcase trust score for Coding agent session journal" height="20"></a>

More engineering workflows

  • Morning ticket dashboard with tick to approve queue

    Every morning an agent refreshes a one screen dashboard in your notes from the issue tracker, your workstream notes and inbox. It reads only, proposes board changes as checkboxes and drafts first pass PR reviews that are never posted.

  • Weekly repo security and docs pulse

    Two weekly runs for people who maintain more repos than they can watch. One opens a single security issue per repo with triaged findings, the other opens one pull request fixing docs that drifted from the code.

  • Pull request reviewer

    Gives every PR a first pass before a person looks.

  • Flaky test hunter

    Finds tests that fail at random and why.