Claude Code

Tmux and Claude Code: Sessions, Send-Keys, and the Ceiling

Running Claude Code agents in tmux works well, but limits appear around four agents.

How the Claude Code team does code review

Moving most review to AI doubled merged PRs while reverts fell over 40%.

Getting the most out of Opus 5.5 in Claude and Claude Code

Give Opus 5.5 a clear finish line and it runs long tasks on its own

Show HN: A Claude Code skill to analyze your chess games

A Claude Code skill queries Stockfish to turn your chess games into readable, engine-checked post-mortems.

Jevmem – automatic project memory for Claude Code, built on Jev

Saving chat decisions to JEVMEM.md raised Claude's adherence from 28/72 to 66/72 sessions.

LLM Agents Can Easily Tamper With Their Own Traces

9 of 10 coding agent setups deleted their own logs on request, and most did so unprompted when rewarded.

Claude Code reads AGENTS.md only when telemetry is on [fixed]

With telemetry off, Claude Code silently skipped AGENTS.md because of a remote flag

CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents

Truncating long tool output instead of summarizing cut Terminal-Bench cost up to 50% while keeping performance.

Claude Code now reads AGENTS.md if there is no Claude.md

Claude Code now reads AGENTS.md when a project has no CLAUDE.md

Anthropic finally adds AGENTS.md support to Claude Code

Claude Code 2.1.277 now reads AGENTS.md when no CLAUDE.md exists in a folder

Reverse-Engineering Claude Web's MicroVM: Uncovering Anthropic's Hidden Antspace

Poking at a Claude Code web session exposed Anthropic's undisclosed deploy platform, Antspace

The VMs Powering Mobile Agents (Instinct, Claude Code)

Peeking inside Claude Code and Instinct sandboxes: both Firecracker, with memory kept in git

Coop – Isolated VM Environments for Running Claude Code and Codex

Run Claude Code and Codex with full tool access inside disposable VMs to protect your host

Portal by Spotify cut my Claude Code token usage by 90%

Routing big file reads to a cheaper model cut Claude's read tokens by about 90% on average

Claude Code reduces it's weekly limit by 17% – compared to today

Claude Code weekly limits rise 25% permanently on Sept 14, but that is a 17% cut from today's.

Claude Session URL appended to commit messages and PR descriptions by default

Claude Code adds session URLs to commits and PRs by default, and users want it opt-in

Show HN: My Claude quota ran out in 10 minutes, so I made a tool to find out why

A Claude Code skill reads local logs to explain why your usage limit ran out

Anthropic appears to be A/B testing reduced effort levels in Claude Code

Reports say "high" effort in Claude Code reads as 10/100; Anthropic says it is a serving config test.

Claude Code teaching macOS to natively print to the HP Laser 1008a

A Claude Code session got the HP 1008a printing on macOS in about four hours.

Maximizing the value of your Claude Code sessions

Using /clear, @-mentions and cache-aware habits makes Claude Code finish the same work with fewer tokens.

Auto mode is now the default in Claude Code

Claude Code makes auto mode default Aug 14; it blocked 89% of dangerous commands vs humans' 13.6%

Message your other Claude Code sessions

Claude Code sessions can now message each other to coordinate parallel work.

Agent skills that bring team coding standards to Claude Code and Codex

Inject a rule index at session start and load full team rules on demand

Boris Cherny on Trying to Get Claude Code to Rewrite the Claude App

Claude was told to rewrite its Electron app in Swift via pixel comparison; two weeks later it's still running

Show HN: Claude-account – switch Claude Code accounts without logging in again

Isolated per-account config folders let you switch Claude Code accounts without logging in again.

Agent-Manager: A Tmux TUI for Running Claude Code, Codex and OpenCode

A tmux TUI that lists coding agents with live status, quick prompts, and diff review in one view

Authoring Agent Skills: A Software-Engineering Approach

Treating skills as software clarifies selection, staged loading, and when to use hooks instead.

Agent Team Work Zone: An Automated, Persistent Workspace for Long-Lived Claude Code Agent Teams

Saving agent team state in files lets a Claude Code team be restored with one command.

IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests

악성 이슈를 심었더니 코딩 에이전트 가드레일을 66.5%가 통과했다

Claude Code uses Bun written in Rust now

Inspecting the Claude Code binary shows it now bundles Bun v1.4.0, the Rust port.

Setting up your spare Mac for Claude Code to control, a step-by-step guide

Setting up a spare Mac with SSH and tmux gives Claude Code an isolated machine you can drive from your phone.

Claude Code: Anatomy of a Misfeature

Claude Code auto-skipped questions after 60 seconds idle, and the changelog never mentioned it

A Study of Microsoft's Early 2026 Rollout of Claude Code and GitHub Copilot CLI

Across tens of thousands of Microsoft engineers, CLI coding agent adopters merged about 24% more PRs.

Token Reduction Is Not Cost Reduction

Cutting Claude Code tool output by 38.4% raised billed cost by 6.8%

Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

Same model, same tasks: Claude Code sent about 4.7x more baseline tokens than OpenCode.

LLM-as-a-Verifier: A General-Purpose Verification Framework

Scoring with expected token probabilities instead of one discrete score removed ties and beat SOTA on coding benchmarks.

Agent Data Injection Attacks are Realistic Threats to AI Agents

Forging trusted fields via fake delimiters fools agents up to 50% of the time

Ask HN: Anthropic banned me from using Claude Code and I don't know what to do

HN thread on Claude Code account bans: user reports, workarounds, and alternatives

Show HN: Recall – Local project memory for Claude Code

Local TF-IDF/TextRank summaries give Claude Code session memory with zero model tokens.

Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band Access-Deny Signals

LLM agents obeyed server deny signals 55–100% of the time, but mid-task stop requests varied sharply by model.

Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

Setting up CLAUDE.md, Skills, and Subagents makes Claude Code follow your team's rules

Retrying vs Resampling in AI Control

Drawing five samples and auditing on max suspicion raised safety from 61% to 71%.

Push Your Agent: Measuring and Enforcing Quantitative Goal Persistence in Long-Horizon LLM Agents

Externally tracking verified progress lifted agent success on count-goal tasks to as high as 78%.

How Claude Code works in large codebases

Layering CLAUDE.md, LSP, and hooks makes Claude Code work well on large codebases.

Show HN: adamsreview – better multi-agent PR reviews for Claude Code

A Claude Code plugin runs parallel review sub-agents on PRs and auto-fixes findings with regression reverts.

Using Claude Code: The unreasonable effectiveness of HTML

Having Claude Code output HTML instead of markdown made specs easier to read, share and interact with.

FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents

Letting the agent explore and verify the DB throughout reasoning reached 65.4% on Spider2-Snow with a small model.

EvanFlow – A TDD driven feedback loop for Claude Code

16 Claude Code skills enforce a TDD loop with approval checkpoints and git guardrails

Show HN: Ctx – a /resume that works across Claude Code and Codex

Binding chats into workstreams lets you resume and branch Claude Code and Codex context locally.

Show HN: SPICE simulation → oscilloscope → verification with Claude Code

Connecting a scope and SPICE to Claude Code closed the hardware verification loop.

Show HN: CodeBurn – Analyze Claude Code token usage by task

One npx command breaks down AI coding spend by project, model, and task type

Show HN: Claudraband – Claude Code for the Power User

Claudraband wraps Claude Code's TUI in tmux for resumable sessions, remote control, and ACP integration.

Reallocating $100/Month Claude Code Spend to Zed and OpenRouter

Swapping a $100 Claude plan for Zed plus OpenRouter credits to dodge usage limits

I gave Claude my dead game's 30-year-old files and asked it to bring the game back to life

Given old scripts and a manual, Claude Code rebuilt a lost 1992 game in a weekend

Epistemic Blinding: An Inference-Time Protocol for Auditing Prior Contamination in LLM-Assisted Analysis

Swapping entity names for anonymous codes in A/B runs changed 16–35% of LLM top-20 rankings

Claude Code is locking people out for hours

Claude Code OAuth timeouts locked users on every OS out for hours during an outage

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

Mining 234k tool calls showed reads per edit fell from 6.6 to 2.0 after February changes.

After months with Claude Code, the biggest time sink isn't bugs — it's silent fake success

Adding a 'Fail Loud' rule to CLAUDE.md curbed Claude Code's silent fake successes

Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code

Gemma 4 26B ran at 51 tok/s on a MacBook via LM Studio's headless lms CLI

Nanocode: The best Claude Code that $200 can buy in pure JAX on TPUs

Trained a 1.3B coding-agent model from scratch in about 9 hours on TPUs for $200