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:
/chronicleis currently an experimental feature. You'll need to run/experimental on(or use the--experimentalflag) 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
/researchfor 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.