Hacker News Reader

bazhandon DeepSeek planning to significantly raise prices

Token Plan Individual for $6/month has Qwen-3.8-max, HappyHorse1.1, Deepseek V4 and GLM-5.2 models.

https://www.alibabacloud.com/en/campaign/ai-token-plan

It was something that was used for token efficiency. Most of the settings and use cases are quite poorly communicated but asking Claude to review the latest release changelog (https://github.com/anthropics/claude-code/blob/main/CHANGELO...) is quite useful. Combined with @"claude-code-guide (agent)" to read it's own docs for settings/configs is super helpful.

The quite useful tool is to use /opusplan along with /codex:rescue (https://github.com/openai/codex-plugin-cc) means you get quite a strongly reviewed plan using native claude + codex without having to implement the mostly useless trust-me-bro plugins and other bs.

bazhandon Claude Sonnet 5

Have you tried '/model opusplan' I've had strong results mixing opus for planning with sonnet implementing.

bazhandon Herdr: Agent multiplexer that lives in your terminal

Been using https://cmux.com for past few months, and runs nicely over ssh + tmux with native tabs.

bazhandon DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost

/advisor is like the old /opusplan mode but for running tasks not just pre-planning. It can work nicely with Sonnet as the main agent and escalates to Opus as needed.

bazhandon Issue: Claude Code is unusable for complex engineering tasks with Feb updates

export CLAUDE_CODE_EFFORT_LEVEL=max

bazhandon Claude Code adjusting down 5hr limits

and now /fast will get you moving quicker but at a premium.

bazhandon Apideck CLI – An AI-agent interface with much lower context consumption than MCP

I ran into this exact problem building a MCP server. 85 tools in experimental mode, ~17k tokens just for the tool manifest before any work starts.

The fix I (well Codex actually) landed on was toolset tiers (minimal/authoring/experimental) controlled by env var, plus phase-gating, now tools are registered but ~80% are "not connected" until you call _connect. The effective listed surface stays pretty small.

Lazy loading basically, not a new concept for people here.

bazhandon Show HN: CC Usage Bar – Check Claude Code usage from your macOS menu bar

this is the vibe coding equivalent of 'hello world' at this stage. Fun tho.

bazhandon Agent Skills

The third most popular skill on skills.sh[1] with 50k/week installs is a link to download a command[2]

[1] https://skills.sh/vercel-labs/agent-skills/web-design-guidel... [2] https://github.com/vercel-labs/agent-skills/blob/main/skills...

All of these SKILLS.md/AGENTS.md/COMMANDS.md are just simple prompts, maybe even some with context links.

And quite dangerous.

bazhandon Anthropic blocks third-party use of Claude Code subscriptions

FWIW this isn’t new, using a Claude/Max subscription auth token as a general-purpose “API key” has been known (and blocked) for ages. OpenCode basically had to impersonate the official Claude Code client to make that work, and it always felt like a loophole that would get patched eventually.

This is exactly why (when OpenCode and Charm/Crush started diverging) Charm chose not to support “use your Claude subscription” auth and went in a different direction (BYOK / multi-provider / etc). They didn’t want to build a product on top of a fragile, unofficial auth path.

And I think there’s a privacy/policy reason tightening this now too: the recent Claude Code update (2.1-ish) pops a “Help improve Claude” prompt in the terminal. If you turn that ON, retention jumps from 30 days to up to 5 years for new/resumed chats/coding sessions (and data can be used for model improvement). If you keep it OFF, you stay on the default 30-day retention. You can also delete data anytime in settings. That consent + retention toggle is hard to enforce cleanly if you’re not in an official client flow, so it makes sense they’re drawing a harder line.

bazhandon Letta Code

How does the memory scale (or not!) over time. If using Letta in a single agent mode, similar to just using claude - how does memory blocks stay relevant and contextual?

I guess what I'm asking is, if there is a memory block limit, is that an issue for self learning over time. Claude as you know just straight up ignores CLAUDE.md and doesnt self-improve it.

bazhandon I built Claude sub-agents that keep my context clean

I like this approach, and it's very similar to what I'm currently using - albeit my use case is to get Claude to automatically invoke the relevant subagents during both planning and build stages.

Subagents using MCP would solve quite a lot of the context preparation required for a successful session. I'm using GLM-4.6 vision/web search MCP in claude code to relative success as the subagents can access these via API (not true MCP behaviour but close enough)

bazhandon Show HN: Vicinae – A native, Raycast-compatible launcher for Linux

Installing (Arch btw), love the UI

bazhandon How to use Claude Code subagents to parallelize development

Can it work without Linear, using md files?

bazhandon Claude Sonnet 4 now supports 1M tokens of context

    Add these settings to your `.claude/settings.json`:

     ```json
     {
       "env": {
         "ANTHROPIC_CUSTOM_HEADERS": {"anthropic-beta":
     "context-1m-2025-08-07"},
         "ANTHROPIC_MODEL": "claude-sonnet-4-20250514",
         "CLAUDE_CODE_MAX_OUTPUT_TOKENS": 8192
       }
     }
     ```

bazhandon Crush: Glamourous AI coding agent for your favourite terminal

opencode allows auth via Anthropic to enable claude max subscription.

bazhandon Crush: Glamourous AI coding agent for your favourite terminal

Very interesting to see so many new TUI tools for llm.

Opencode allows auth via Claude Max, which is a huge plus over requiring API (ANTHROPIC_API_KEY)

bazhandon Track your Claude Code usage

Interesting, how does this compare against https://github.com/ryoppippi/ccusage ?

bazhandon Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

You may be interested in https://github.com/ryoppippi/ccusage

bazhandon Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs

I like this solution, I had tinkered with the Otel hoping to get un-redacted prompt and responses but had no luck. Did you perhaps get deeper into what data was useful?

bazhandon A look at Cloudflare's AI-coded OAuth library

As a non developer, this was incredible useful to understand the prompt structure and apply to my own Claude Code.

bazhandon Claude's Max Plan

Having used Claude daily for last year or so, I don't feel great about being pushed into quite expensive tiers of 5-20x cost. I already feel like I'm hitting the Pro limit 2x/day more often than recently, although no data to support this - but the feeling is there.

Mostly I'm disappointed that the higher tiers are just usage tiers rather than features.

bazhandon Show HN: Amurex – A cursor like copilot for meetings but also open source

Post sign-up, hitting "Connect Google Services" received this error.

You can’t sign in because this app sent an invalid request. You can try again later or contact the developer about this issue. Learn more about this error If you are a developer of this app, see error details. Error 400: redirect_uri_mismatch

bazhandon Tell HN: Stripe Destroyed Our Business after 7 months of building our product

Did you contact them in the last 7 months, not last 7 hours when you got banned.

bazhandon Tell HN: Stripe Destroyed Our Business after 7 months of building our product

If I understand correctly:

- you run advertising and lead gen on behalf of clients using their CRM (their domain email/outreach)

- and require Stripe for attribution, and to remit payment from client to you

That's most likely triggering Stripe's TOS.

For something so core to your business, did you have a discussion with Stripe if this was allowed?

bazhandon Show HN: Location Finder – Find the best location to meet your remote team

I was looking for a tool exactly like this not too long ago.

Some observations - clicking browser back button loses inputs - ukraine not available? - needs date/month selectors to plan ahead

bazhandon Ask HN: Share your favorite YouTube channels focused on mastering a skill/craft

BaremetalHW is niche, but it's restoring and modding toy cars, primarily Hot Wheels.

The creator has quite a soothing demeanour.

https://www.youtube.com/@baremetalHW

bazhandon Red Dead Redemption 2 fan with 6k hours on Stadia begs for character transfer

The real travesty is sinking so much time into Red Dead Online. It's a quite average experience that's been neglected by Rockstar.

bazhandon Swedish tech startups and scaleups

I joined Proxify (on the list) recently and was pleasantly surprised to find a quite vibrant tech scene. As someone who followed the more traditional startup hubs like Amsterdam, Berlin or Dublin, I've found that there are many gems in the Nordics.