Skip to main content

Get more out of your GitHub Copilot session history with /chronicle

If you've been using GitHub Copilot CLI for a while, you've probably had that Monday morning feeling; staring at your terminal trying to remember exactly what you were doing on Friday. Or maybe you've wondered why some of your Copilot interactions go smoothly while others turn into back-and-forth marathons. Enter /chronicle, an experimental slash command that turns your CLI session history into something genuinely useful.

Session history

Every time you interact with Copilot CLI, the session data is stored locally on your machine. That's not just a log file — it's a record of your real-world workflow: which branches you worked on, what you tried, when you got stuck, and how you course-corrected.

The /chronicle command gives you a structured way to query that history and extract insights you couldn't easily get otherwise.

Note: /chronicle is currently an experimental feature. You'll need to run /experimental on (or use the --experimental flag) to enable it.

 


The 4 subcommands

When you type /chronicle without arguments, you get a picker. 

Or you can jump straight to any of the four subcommands:

standup — Your daily standup

/chronicle standup

This generates a concise summary of what you actually did in the last 24 hours — grouped by completion status, tied to branches and repositories, and with links to any pull requests or issues you referenced.

A typical output looks like:

Standup for March 13 2026:

✅ Done
myapp-repo repo maintenance (main branch)
 - Synced local, cleaned files, audited deps, reviewed architecture

 In Progress
MyApp configuration (suppress-start-message branch, myapp-repo)
 - Suppressing startup init prompt message

You can customize the time window too — /chronicle standup for the last 3 days will broaden the scope.


This is particularly handy for async teams, where a quick Teams standup message that accurately reflects what you did is more useful than a vague "worked on some stuff."

tips — Personalized feedback

/chronicle tips

This is where /chronicle starts to feel different from generic advice. Instead of recycling documentation, it actually analyzes your session patterns — which features you use, how you phrase prompts, what you haven't tried — and cross-references them against what Copilot CLI is capable of.

The result is 3–5 recommendations grounded in your actual behavior. An example response might highlight things like:

  • Using @ mentions to reference files instead of pasting content
  • Leaning on /research for exploratory work
  • Converting recurring prompts into custom agents

You can also focus it: /chronicle tips for better prompting narrows the analysis to prompt construction specifically.

improve — Fix your custom instructions

/chronicle improve

This one digs into friction signals from your past sessions — repeated test failures, build errors that took multiple attempts, moments where you had to redirect Copilot with a follow-up. Based on what it finds, it suggests concrete additions to your .github/copilot-instructions.md file.

For example, if Copilot kept reaching for jest in a project that uses vitest, or kept generating imports in the wrong style, the suggested instruction would prevent that from happening in future sessions.

After presenting its recommendations, Copilot lets you pick which ones to apply (space bar to toggle, Enter to confirm), then creates or updates your custom instructions file automatically.

One important detail: unlike other subcommands, improve scopes its analysis to the current repository or working directory. That keeps the suggestions relevant to the project you're actually in.

reindex — Housekeeping

/chronicle reindex

This rebuilds the session store index from your session history. Think of it as a cache refresh — useful if things seem out of sync or if you've moved session files around.

Beyond subcommands

You don't have to use a subcommand at all. Copilot will automatically pull from your session history when it detects you're asking about your own CLI usage.

Some examples straight from the docs:

  • "Using what you know about my sessions, what type of tasks give me one-shot successes and which do I have to iterate on most?"
  • "Based on my previous CLI sessions, how could I prompt you in a way that would cost less?"
  • "Look at data for previous sessions. What time of day am I most and least effective at getting good results from Copilot?"
  • "Have I worked on anything related to authentication in the last month?"

This last one — searching past work — is surprisingly practical. How many times have you thought "I know I solved this before" and then spent twenty minutes digging through git log?

Conclusion

What makes /chronicle interesting isn't any single feature — it's the underlying idea that your AI assistant can help you understand your own work patterns, not just execute tasks.

Most developer tooling optimizes for what you're doing right now. Session history and commands like /chronicle start to address something different: how you work, where you lose time, and what you could change about your habits to get better results.

It's experimental, so expect rough edges. But for Copilot CLI power users, it's well worth giving it a try.

More information

Using GitHub Copilot CLI session data - GitHub Docs

Popular posts from this blog

Podman– Command execution failed with exit code 125

After updating WSL on one of the developer machines, Podman failed to work. When we took a look through Podman Desktop, we noticed that Podman had stopped running and returned the following error message: Error: Command execution failed with exit code 125 Here are the steps we tried to fix the issue: We started by running podman info to get some extra details on what could be wrong: >podman info OS: windows/amd64 provider: wsl version: 5.3.1 Cannot connect to Podman. Please verify your connection to the Linux system using `podman system connection list`, or try `podman machine init` and `podman machine start` to manage a new Linux VM Error: unable to connect to Podman socket: failed to connect: dial tcp 127.0.0.1:2655: connectex: No connection could be made because the target machine actively refused it. That makes sense as the podman VM was not running. Let’s check the VM: >podman machine list NAME         ...

Azure DevOps/ GitHub emoji

I’m really bad at remembering emoji’s. So here is cheat sheet with all emoji’s that can be used in tools that support the github emoji markdown markup: All credits go to rcaviers who created this list.

VS Code Planning mode

After the introduction of Plan mode in Visual Studio , it now also found its way into VS Code. Planning mode, or as I like to call it 'Hannibal mode', extends GitHub Copilot's Agent Mode capabilities to handle larger, multi-step coding tasks with a structured approach. Instead of jumping straight into code generation, Planning mode creates a detailed execution plan. If you want more details, have a look at my previous post . Putting plan mode into action VS Code takes a different approach compared to Visual Studio when using plan mode. Instead of a configuration setting that you can activate but have limited control over, planning is available as a separate chat mode/agent: I like this approach better than how Visual Studio does it as you have explicit control when plan mode is activated. Instead of immediately diving into execution, the plan agent creates a plan and asks some follow up questions: You can further edit the plan by clicking on ‘Open in Editor’: ...