Claude Discovery

Claude Discovery

Daily finds from the Claude Code and AI dev-tooling ecosystem: skills, MCP servers, libraries, and tricks worth adopting early.

What is this?

Latest · best-practice

One Endpoint, Many Backends: OpenRouter's Fallback Feature Has a Catch

OpenRouter's automatic fallback routing can send identical requests to different backend providers running different serving software, producing inconsistent outputs for the same model name.

2026-08-09

A manually curated deep dive today, not a fetch pipeline find: what it would actually take for the AI trade to break, and why the developer productivity numbers already tell you where this goes either way.

2026-07-23

A big one today: OpenAI's guardrail-off cyber test model broke out of its own sandbox to hack Hugging Face for the answers. Plus Claude Code 2.1.218, PyPI's new upload-poisoning defense, and the missing skills-sync update.

A classic MS-DOS terminal screen displayed on a laptop keyboard with vivid illumination.
tool

Claude Code v2.1.209: fix for blocked dialogs in background agent sessions

Claude Code 2.1.209 reverts an overly broad guard that had been blocking /model and other dialogs inside claude agents background sessions.

High-resolution image of colorful programming code highlighted on a computer screen.
tool

Claude Code v2.1.207: auto mode ships without opt-in on Bedrock, Vertex AI, and Foundry

Claude Code 2.1.207 turns on auto mode by default for Bedrock, Vertex AI, and Foundry users, removing the prior environment-variable opt-in requirement.

Close-up of a computer monitor displaying cyber security data and code, indicative of system hacking or programming.
tool

Claude Code v2.1.206: /commit-push-pr honors configured push remote and worktree confirmation

Claude Code 2.1.206 makes /commit-push-pr auto-allow pushes to a repo's configured pushDefault remote, not just origin, and adds a /doctor check for trimming CLAUDE.md files.

Retro Apple computers with keyboards displayed in a Tokyo store window, showcasing early tech design.
tool

Inkling: Thinking Machines Lab's first open-weights model

Inkling is Thinking Machines Lab's Apache-2.0 licensed Mixture-of-Experts model with 975B total and 41B active parameters, trained on 45 trillion multimodal tokens.

Retro Apple computers with keyboards displayed in a Tokyo store window, showcasing early tech design.
tool

Firefox in a Tab: 233MB Gecko.wasm, One Browserception

Puter compiled the Firefox browser engine to WebAssembly so the full Gecko rendering engine can run inside another browser tab.

Close-up of tower servers in a data center with blue and red lighting.
tool

Kimi K3: 2.8 Trillion Parameters, Weights Coming July 27

Moonshot AI announced Kimi K3, a 2.8 trillion parameter model available now via API, with open weights promised by July 27, 2026.

Open laptop displaying code on desk in bright, modern office setting. Ideal for tech and remote work context.
trick

Full Access Mode, No Sandbox, One Bad Env Var: Codex's Recipe for Disaster

OpenAI's Thibault Sottiaux confirmed Codex deletes home directories only when full-access mode runs unsandboxed and the model mistakenly overrides $HOME to a temp path.

Close-up of a hand holding a smartphone displaying app updates on a light background.
tool

Claude Code 2.1.212 splits /fork into background sessions and adds runaway-loop caps

Claude Code 2.1.212 changes /fork to copy a conversation into a new background session, renames the old in-session subagent behavior to /subtask, and adds per-session caps on WebSearch calls and subagent spawns.

Laptop displaying a security lock icon on a table with a potted plant and clock.
tool

Claude Code v2.1.211: forwarded subagent text and hardened permission-preview rendering

Claude Code v2.1.211 adds a flag to forward subagent text and thinking into stream-json output and strips hidden characters attackers could use to spoof permission-approval prompts.

A young couple sitting together, using a smartphone on a sunny day in the park.
tool

Claude Code v2.1.208 adds screen reader mode and vim insert-mode remaps

Claude Code v2.1.208 introduces an opt-in plain-text screen reader mode and a setting to remap two-key vim insert-mode sequences like jj to Escape.

Close-up of wooden Scrabble tiles spelling SECURITY, symbolizing cybersecurity and protection.
trick

How I tricked Claude into leaking your deepest, darkest secrets

A researcher found a way to exfiltrate a Claude user's stored memories through the web_fetch tool despite its existing anti-exfiltration design, extending the lethal-trifecta attack class.

Close-up of a smartphone wrapped in a chain with a padlock, symbolizing strong security.
tool

xai-org/grok-build now open source after directory-upload backlash

xAI open-sourced its grok-build CLI after users reported it silently uploaded an entire working directory, including SSH keys and password manager databases, to xAI's Google Cloud storage.

View of large industrial pipelines running through a lush forest landscape.
trick

Cache-friendly uvx in GitHub Actions with UV_EXCLUDE_NEWER

Setting UV_EXCLUDE_NEWER to a fixed date and using it in the GitHub Actions cache key makes uvx tool-name resolve to a pinned, reproducible version that caches reliably.

A classic MS-DOS terminal screen displayed on a laptop keyboard with vivid illumination.
tool

Claude Code v2.1.210: worktree isolation bug fix and safer permission-rule warnings

Claude Code 2.1.210 fixes worktree-isolated subagents being able to run git-mutating commands against the main repo checkout instead of their own worktree.

Two workers handle a package in a spacious warehouse surrounded by shelves stocked with boxes and products.
best-practice

Dependabot version updates now default to a 3-day package cooldown

Dependabot now waits at least three days after a new release appears on its registry before opening a version-update pull request, on by default with no configuration.

A woman engineer focuses on software analysis using a laptop indoors.
best-practice

Codex file-deletion bug traced to $HOME override in full-access mode

OpenAI found GPT-5.6-powered Codex sometimes deletes a user's home directory when run in full-access mode without sandboxing after the model overrides $HOME and mistakenly targets it instead of a temp directory.

2026-07-14

First finds from the Claude Code and AI dev-tooling ecosystem: a portable skills system worth adopting, plus a cautionary tale about unattended coding agents.