Claude Directory opens a submission flow for plugins, Video
Plugin and MCP Connector builders get their own door into Claude Directory, a new submission flow, and according to Claude's website, plugin usage stats come with it.
Tags
Tag: developer-tools
Microsoft Copilot gets a Code mode on GitHub Copilot tech, Video
Three modes in Microsoft's new Copilot app, and Code runs on the same tech as GitHub Copilot, with a new Managed Copilot Runtime to execute code. It's rolling out now, though only through the Frontier program.
Cursor's new bot follows each pull request into production
Open a pull request in Cursor and a bot called Rollouts drafts a monitoring plan before the code ships. After deploy it checks logs and metrics against that plan, but it won't roll back a deployment by itself.
Four Opus 5.5 API changes make Opus 5 requests fail
$4 per million input tokens instead of $5 makes Opus 5.5 look like an easy upgrade, but Anthropic's migration guide lists four changes that make Opus 5 requests fail with 400 errors.
Claude Code skips AGENTS.md when telemetry is off
Switching off telemetry in Claude Code also quietly disabled a feature that only reads a local file. AGENTS.md support waits on a remote flag that falls back to false, and nothing tells you the file was skipped.
Code strings point to a $50 production plan for OpenAI's API
$50 is where Accelerate starts, the production plan in a three-tier API onboarding flow spotted in OpenAI Platform strings. Below it sit Prototype and a Free tier that routes API access through Codex.
GPT-6 caching update cuts cached input costs by up to 90%
Developers who resend the same long system prompt on every GPT-6 call will pay less for that repeated part, since OpenAI's caching update cuts cached input token costs by up to 90%.
JetBrains folds its agent tools into one brand, Air
26 years of building IDEs like IntelliJ IDEA and PyCharm, and JetBrains' CEO calls Air one of the company's most significant steps. It pulls outside agents like Claude Code and Codex under one roof, and it still bets on the IDE.
FutureOS kept 147 of 178 answers, Codex kept 68
Tool output is 96.1% of the characters in a filled agent context window, but only 10% of later questions point at it. FutureOS's 178-question compaction test scores that mismatch: its default kept 147 answers, Codex 68.
Anthropic's Playground shows the cost of each API call
Tokens, cost, and latency now sit next to every request in Anthropic's Claude API sandbox, renamed from Workbench to Playground, per a Threads post. The SDK code copies out when something works.
Nvidia backs a shared exchange for agent failure reports
The best coding agents fail more than 60% of the time on tasks drawn from real codebases, and Nvidia's Adel el Hallak says logs won't tell you why: roughly 140 companies are pooling agent failure reports in SAFE.
Notion and Granola are first through Meta's Muse Connectors
Meta wired Stripe into its Muse agent so purchases can run through a developer's product, and opened Connectors so anyone can submit one. Notion and Granola are already on the list.
Grok Build starts remembering how your team runs tests
Grok Build ran cargo test, the test database wasn't up, and the user explained that just test starts it first. xAI's new memory keeps that correction as a note and applies it in the next session.
libheif bugs reached OpenAI repos and GitHub Enterprise
One image parser to pwn them all Hacktron says a crafted .heic upload could have dumped OpenAI's private repositories. Some of its RCE attempts landed only after thousands of uploads.
OpenAI's lawyers and recruiters now work through Codex
Codex took over OpenAI's legal and finance desks Finance, recruiters and lawyers at OpenAI set a goal in Codex and let the thread run for days. Per The Pragmatic Engineer, those teams went from roughly 0% usage to 90% in four months, with no mandate from above.
Jev runs 1,000 code reviews for $0.04, scoring 98%
1,000 code reviews for $0.04 The same rule check scaled to 1,000 reviews runs $0.043 on Jev against $11.78 on Claude Fable, from 360 calls per model. Jev pays in accuracy: 98% correctness where Fable scores 100%.
Copilot rewrote its own runtime into 800,000 lines of Rust
Copilot's own agents typed most of GitHub's agent runtime rewrite: more than 800,000 lines of production Rust, mainly one developer over a few months, where a team would have needed a year or two.
TypeSafe AI's Jev answers with choices, never sentences
Jev replies with a typed decision and a score "Why have superhuman chat models not led to AGI?" Diogo Almeida asked that, then spent two years in stealth on Jev, a model that hands back one option from a developer-defined list instead of text.
Every chatgpt.com page carries 377 KB of flag decisions
377 KB of flags in every page A teardown of chatgpt.com found the whole experiment state inlined per request: 556 gates, answered before React hydrates. The names are hashed numbers, so leakers can't read the roadmap.
Zed killed pull requests on its own repo, then shipped Delta
Zed switched off pull requests on its own Delta repo, and 33 developers have since landed 570 changes to main without one. Delta's public beta is open, though Zed still leans on GitHub for Git storage and CI.
