Hacker News: bazhand

New comment by bazhand in "Claude Sonnet 5"

bazhand — Tue, 30 Jun 2026 20:36:14 +0000

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.

New comment by bazhand in "Claude Sonnet 5"

bazhand — Tue, 30 Jun 2026 19:31:12 +0000

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

New comment by bazhand in "Herdr: Agent multiplexer that lives in your terminal"

bazhand — Mon, 29 Jun 2026 18:18:23 +0000

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

New comment by bazhand in "DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost"

bazhand — Sun, 24 May 2026 21:25:58 +0000

/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.

New comment by bazhand in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

bazhand — Mon, 06 Apr 2026 22:26:27 +0000

export CLAUDE_CODE_EFFORT_LEVEL=max

New comment by bazhand in "Claude Code adjusting down 5hr limits"

bazhand — Fri, 27 Mar 2026 17:54:06 +0000

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

New comment by bazhand in "Apideck CLI – An AI-agent interface with much lower context consumption than MCP"

bazhand — Mon, 16 Mar 2026 18:55:08 +0000

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.

New comment by bazhand in "Show HN: CC Usage Bar – Check Claude Code usage from your macOS menu bar"

bazhand — Sat, 07 Mar 2026 23:09:37 +0000

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

New comment by bazhand in "Agent Skills"

bazhand — Tue, 03 Feb 2026 20:52:07 +0000

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.

New comment by bazhand in "Anthropic blocks third-party use of Claude Code subscriptions"

bazhand — Fri, 09 Jan 2026 08:41:41 +0000

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.

New comment by bazhand in "Letta Code"

bazhand — Wed, 17 Dec 2025 18:02:33 +0000

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.

New comment by bazhand in "I built Claude sub-agents that keep my context clean"

bazhand — Wed, 15 Oct 2025 11:36:41 +0000

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)

New comment by bazhand in "Show HN: Vicinae – A native, Raycast-compatible launcher for Linux"

bazhand — Wed, 10 Sep 2025 06:11:08 +0000

Installing (Arch btw), love the UI

New comment by bazhand in "How to use Claude Code subagents to parallelize development"

bazhand — Tue, 09 Sep 2025 21:20:04 +0000

Can it work without Linear, using md files?

New comment by bazhand in "Claude Sonnet 4 now supports 1M tokens of context"

bazhand — Tue, 12 Aug 2025 21:56:03 +0000

    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
       }
     }
     ```

New comment by bazhand in "Crush: Glamourous AI coding agent for your favourite terminal"

bazhand — Thu, 31 Jul 2025 16:44:07 +0000

opencode allows auth via Anthropic to enable claude max subscription.

New comment by bazhand in "Crush: Glamourous AI coding agent for your favourite terminal"

bazhand — Thu, 31 Jul 2025 11:23:27 +0000

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)

New comment by bazhand in "Track your Claude Code usage"

bazhand — Tue, 15 Jul 2025 17:42:30 +0000

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

New comment by bazhand in "Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs"

bazhand — Sun, 22 Jun 2025 09:41:02 +0000

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

New comment by bazhand in "Show HN: Claude Code Usage Monitor – real-time tracker to dodge usage cut-offs"

bazhand — Thu, 19 Jun 2025 17:16:38 +0000

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?