Hiranmaya retweeted
Weekend is here.
Late night grind, Valorant on the side.
What are you guys up to?
Hiranmaya retweeted
300 verified done
And a lot of impressions away
Long way to go but the grind is on
What does this look like for you guys?
Hiranmaya retweeted
Real talk:
AI made me faster and worse.
Faster at writing code.Worse at figuring out why something's broken.
Anyone else, or just me?
Hiranmaya retweeted
To-do apps are easy. Following through is the hard part.
Meet TiniDo. After months of building, finally out of my head. Brain-dump one messy line, get a real reminder. Streaks that bend instead of breaking. One thing at a time.
Launching this month for @RevenueCat's Shipaton!
Hiranmaya retweeted
"I'll launch when it's ready"
Is that craftsmanship
Or is that fear with a nicer word?
Hiranmaya retweeted
Finally time!!
Fable 5 was already so awesome and now I wonder what Fable 5.1 is gonna be like. Well, today's gonna be a long night 😁
Happy building everyone 🍻 – at Bhubaneshwar, India
Hiranmaya retweeted
5 days of trying to stay consistent and All this green definitely helps 😁
Let’s keep it going 💪
Hiranmaya retweeted
Claude can't watch a screen recording, but it can look at the frames.
I've been using /frex for this. Give it a video and tell it what to look for and it extracts frames with ffmpeg & hands them to a subagent, so they never touch your main context.
I don't tune the range or frame rate. I just describe what feels wrong and let it figure out where to look.
A few things it's actually caught for me: a transition landing a beat late, a card overshooting before it settles, two elements kicking off together when they should've been staggered.
Things I could feel were wrong, but couldn't point at.
Hiranmaya retweeted
7 days of hectic life and I'm back to the grind. Really very grateful.
I hate being inconsistent when so many things are going on. Lots of things happening and lots to post about!!
Slowly and steadily, trying to pave my way back 😁✌️ – at Bhubaneshwar, India
Hiranmaya retweeted
Feeling really good about how my app is coming together right now. Gonna start posting more about it and I'm excited for what's ahead 😁 – at Bengaluru South, India
Hiranmaya retweeted
One thing I've learned with Claude Code:
Upgrading your workflow often has a bigger impact than upgrading your model.
Custom MD files, skills, MCPs, and plugins have improved my results far more than any prompting trick.
The more project knowledge and capabilities you can externalize, the less Claude has to infer and the better it performs.
I'm just going to dump my whole agentic setup out here, because I see too many people missing giant chunks of this and it's hurting them.
Here's what I have and recommend:
0. an AGENTS.md that is a router -- it sends the agent to the right skills, docs, tools
1. a standard workflow doc/skill customized to my needs ... (grab Matt Pocock skills if you don't already have something) ... I tag this in most sessions with `@/AGENT_WORKFLOW.md` and it pulls it in.
2. self-healing docs for every system, and agents are instructed to keep them updated ... I tag the ones I know I need, or let the agent find them through AGENTS.md ... I also provide a more detailed summary in the first 7 lines of every doc, so they're easily greppable to find the right thing, and this is documented in AGENTS.md
3. agents always run the app ... the agent should always actually run the app itself, and test its work and fix issues as it goes, especially if running autonomously / asynchronously
4. end-to-end tests and instructions to write more and keep up to date, and docs on how to write tests, what to avoid, and a list of all the tests and what they test in yet another markdown doc ... write and run targeted tests during implementation, improve and commit with work
5. custom linters at precommit hooks looking for any problems you run across, with `--fix` fixing the problems automatically, OR if that's not feasible, it shells out to a cheaper LLM like Composer 2.5 or Sonnet to fix the problems -- NOT just flagging them, but actually resulting in cleaned code
6. cross-agent review at each major point: research, plan, implementation, and wrap-up. I mean codex, claude, cursor, whatever -- but it shouldn't be the same model reviewing the same code. And specific docs for agent review, what to look for, how to approach it. Also, personas -- looking at the code from different perspectives, such as maintainability, code quality, security, performance, AI smells, domains (e.g. "financial services expert" or whatever) ... and each persona also "owns" a set of system docs too and keeps them up to date
7. agent traces / worksheets that track what the agent is doing each session. if the agent fails partway through, you should be able to hand this worksheet to another agent and it could finish the job. commit this worksheet with the work so it's all connected and easy to reference later (you will reference these later!!), also have the agent apply git tags that correspond to specific worksheet names so they're easy to find
8. automatic agent feedback to you at the end of the session, added to a doc that is also committed with the work, that you periodically ingest into an interactive session and improve your workflows
9. a tools or bin folder that contains python or bash scripts that the agent has skills to make to make its job easier (for example, I have an `agent_review` bash script that lets the agent kick off agent reviews via CLI without knowing each agent's particular incantations) ... docs on how to make scripts effectively, and instructions to constantly build these out more
10. periodic agent sweeps through recent commits, looking for problems / gotchas from a higher level across commits
11. a coding conventions doc that is just for specific coding conventions you want to see in the code base, your review agents use these a lot (but a lot of this should be in linters)
12. an agent loop / night shift skill for autonomous work, that lays out how the agent is to approach this, from an orchestration standpoint
13. a task queue that is accessible to the agent (mine is just a TODOS.md, but yours might be in Linear etc, with a CLI to fetch via API)
14. a periodic false-confidence test audit skill that looks for tests that aren't actually testing what you think they're testing, and that fix those
15. visual regression tests -- take screenshots, compare via tool and with agent visual review, commit with work (git lfs useful here) or at least push into the PR
16. automatic performance benchmark tests that notice when performance degrades
17. performance profiling tools that can be used by agents for targeted benchmarking, trying new techniques, comparing outputs, and comparing profiles
18. end-of-shift full validations, including running all tests, performance, agent reviews, sweeps, everything -- when you return, it's all as pristine as it can be
If you have all this, your agentic coding experience is going to be very different than dry prompting and manually guiding it toward the right thing every time.
Hiranmaya retweeted
Empty State is a pattern that appears when there is no content to display, guiding users on what to do next. It transforms a moment of absence into an opportunity for clarity, providing instructions, encouragement, or actions that help users move forward.
The strength of an empty state lies in its ability to turn a blank screen into a purposeful interaction.
Hiranmaya retweeted
I saw a dream last night that Claude Opus 4.7 dropped
Already building something with it. Fully locked in
Woke up and immediately checked X to see if it was real.
It wasn't 😭
At what point did AI take over my subconscious?
Am I cooked guys? 🫠













