Spotlight by Backplanes - Session reports for Claude Code & Codex to improve your code

@artstavenka1 Thanks, Art! Definitely deliberate, but one (good!) clarification: it's not limited to being post-session. Spotlight reports actually build while you work, just minutes behind your agent, so you're not waiting for a session to end to find out what happened.

What we deliberately avoided is the inline path. A guardrail that interrupts mid-write has to sit between you and the model, with the latency and potential breakage that path implies, and we very much want to help keep you in flow. :)

@luca_capone, "the secret you committed three sessions ago" is almost word-for-word how Spotlight actually started for us: I asked Claude to fix one file, and an API key ended up in a tracked .env that we only caught by accident. So yes, security is very much called out specifically, and it leads the report rather than riding along. Findings arrive severity-ordered in their own stream: secrets landing in files git tracks, prod-touching commands that skipped a dry run, an agent quietly reaching a service you've never used, each with the evidence behind it and a concrete fix.

Code quality and patterns that can help make you more effective with your harness are in there too, so the report always gives you value, even when there are no security-related findings. And since those transcripts are already sitting on your machine, the first report can start with the sessions you've already run. Your "three sessions ago" is still catchable. :)

@luca_capone exactly! Would love for you to give Spotlight a spin and tell us what lands for you, and what we could improve!

@anand_thakkar1, that war story could be one of ours: an agent improvising around a missing env var by quietly inlining the key is the kind of move nobody catches in review. One small correction, it's not OS-level instrumentation. Spotlight reads only the session transcripts the harnesses themselves write, nothing else on your machine. But your key insight holds: it's what the tools actually did, not what the agent says it did.

On fixtures vs leakage, we treat those as two different jobs. Redaction is deliberately paranoid: anything secret-shaped gets masked on your machine before upload, fixtures included, because that step shouldn't be guessing intent. The judgment lives in the analysis: where the credential landed, whether it looks live, and what the session was doing at the time, with severity reflecting that context. A dummy key in a test fixture and a live-looking key written into a tracked file are very different findings. Every finding carries its evidence, so on close calls you're the judge, with the receipts in front of you.

We'd rather flag a fixture at low severity than miss a live key. That asymmetry is on purpose.

Thanks for the support! Let's spread the word on LinkedIn, repost this

@kcpike framing this! S/O to ?makers for building this

@kcpike "Nothing closes the loop back to the human" is the cleanest statement of the problem I've seen yet. :) That's exactly it: review used to be where engineers got better, and agents quietly took that away while speeding everything else up.

@kcpike 1000% Everything is changing under our feet at a crazy rate, so the faster we learn and improve the better we get and the faster we all go! Recursively compounding returns!

@yrechtman "Rad and kind of terrifying" is the almost universal reaction so far. ;-)

It's the bar tab after a great night: the fun was real, and now there's an itemized record of exactly how.

The difference is this tab works for you. It shows what drove the cost, and the biggest line items usually turn out to be the easiest fixes: the same dead end paid for ten times, an agent left grinding away on the wrong thing.

Curious to hear if your next session's number behaves.

Thanks, @farrukh_butt1 "quietly" is the certainly operative word: the touching, breaking, and exposing all happen mid-flow, in the part nobody's watching, while the shipped code gets all the attention. :)

@richiebonilla agreed! we think there's a real opportunity here for Spotlight to help build better skills for engineers on the fly based on the content of these reports. We're excited to make engineers who use coding harnesses faster, safer and more cost effective!

@richiebonilla, "a bespoke string of skills run by hand" is exactly the ritual we kept finding, and living ourselves. Replacing yours is about the highest compliment a tool like this can get, so thank you.

@louislecat lfg! here you go: backplanes.com

looking forward to your thoughts

@louislecat amazing! excited to hear what you think and what you'd like us to build next!

@kevinzrzgg, you seem to have written our report spec almost exactly. :)

Changed files: all files read and written are in there. Tests and checks: flagged with their outcomes when the session shows them. Failed attempts: called out, including the distinction between deliberate re-verification and flailing retries. "What a human should look at first": that's the top of the report, a one-line verdict with the main outcome, then findings ordered by severity and guidance on what to do for each.

The one we can only claim half credit on is risky assumptions: concrete risky choices surface as findings, and a blind-spots section names what the report couldn't verify, but a dedicated assumptions section is a great idea.

And we're with you on boring: the standing rule inside the report is no invented findings and no padded advice, an empty section beats a manufactured one.

@conduit_design Ha, right?! The wild part: that's the agents' own tab, we just hand you the receipt. It's crazy how quickly token usage accelerates when you're running multiple subagents on an intensive job, and Fable pricing is going to make this even more fun for all of us soon. 😅

On "recursively better," the idea is that it's a loop with you in it. The model never changes; your setup does. Each report turns what happened into concrete and actionable advice: a fix to apply, a CLAUDE.md line to include, a Skill to draft. Your agent loads that richer setup next session and starts more informed than the last one.