Topic hub · 14 pieces

Coding agents

Coding agents moved from editor plugins to infrastructure in 2026. At a background-agents summit Ona hosted three weeks before OpenAI agreed to acquire it on June 11, engineers reported agents writing 11% of Uber's merged pull requests and more than 1,000 fully agent-written pull requests a week at Stripe. SpaceX completed its merger with Cursor's parent on August 14 at an implied $60.0 billion equity value.

Model supply now follows ownership. OpenAI gave notice on August 28 that it would stop serving models to Cursor from a proposed November 12 shutoff, and Anthropic, which pays SpaceX $1.25 billion a month for compute, promised Cursor more Claude capacity the same night. The pieces below cover the tools in daily use and the deals that decide which models reach them.

Timeline

  1. · Tools

    Stop using Claude Code like a chatbot

    The Claude Code config Boris Cherny actually runs — settings.json layers, permissions, plan mode, memory, hooks, skills, subagents, MCPs, sandboxing, and the 5-worktree workflow.

  2. · Tools

    gstack: every skill, every command, and who should use it

    Garry Tan's gstack passed 101,020 GitHub stars in ten weeks with 33 slash commands, 7 standalone CLIs and 4 OpenClaw skills, and this full reference covers every skill with three concrete examples and decodes the LOC controversy.

  3. · Agents

    Grok Build, and the model xAI didn't make

    xAI shipped a terminal coding agent, then put a competitor's model inside it that out-codes its own; read against a $60B SpaceX option on Cursor, the CLI war looks less like four rivals and more like one stack assembling itself.

  4. · Tools

    Stop using OpenCode like a Claude Code clone

    The OpenCode config that earns its keep — opencode.json layers, the build/plan agents, permissions, AGENTS.md, MCP, and the bring-your-own-model setup that survives a vendor pulling your access.

  5. · Tools

    Stop fighting Codex CLI's approval prompts

    The Codex CLI config that ends the permission nagging — config.toml profiles, sandbox and approval modes, AGENTS.md, reasoning effort, MCP servers, and the codex exec setup for CI.

  6. · Agents

    Who owns the coding-agent runtime?

    In 48 hours the question of where long-running coding agents actually run got both answers at once: an indie $7M bet against lock-in, and a frontier-lab acquisition that pulls the runtime layer inside Codex.

  7. · Agents

    Cursor Compile 2026: the vertical stack lands, and a warning on the same stage

    At its first Compile conference, Cursor announced a from-scratch model on SpaceX compute, Origin (a GitHub rival), and Cursor Mobile, while its design lead used the stage to warn the result could be slop with working buttons.

  8. · Agents

    The Cursor SDK and the year the coding agent stopped being an editor

    Notion embedded coding agents into its workspace in a few weeks with the Cursor SDK, which turns the harness behind Cursor into a callable runtime so an @mention can plan, build, test and open a PR, a bigger shift than any model release.

  9. · Models

    Three labs shipped. One asked permission.

    In 72 hours in early July, SpaceXAI shipped Grok 4.5, Meta shipped Muse Image and Muse Spark 1.1 and OpenAI shipped GPT-Live while GPT-5.6 Sol waited on a government review, and the real frontier, agentic coding at $2 a million tokens, routed straight around that gate.

  10. · Business

    Emergent is a $1.5B unicorn in six months. What are we pricing?

    An Indian vibe-coding startup quintupled its valuation to $1.5B in half a year on a genuine $120M revenue run-rate, leaving open what the multiple is buying when the model underneath is rented and the interface is copyable.

  11. · Business

    OpenAI gives SpaceX notice: no OpenAI models in Cursor after November 12

    Two weeks after SpaceX closed its $60 billion merger with Cursor's parent, OpenAI used a change-of-control clause to wind down its model contract by a proposed November 12 shutoff, citing Musk companies' record on contracts and withholding its next model, Astra.

  12. · Models

    GPT-6.1 Sol costs a fifth of Astra. Fast Sol costs more than Astra.

    GPT-6.1 Sol ties GPT-6 Astra on OpenAI's own coding benchmark at $2 and $10 per million tokens, a fifth of Astra's rate, but its Ultrafast tier costs $12 and $60, which moves OpenAI's price premium from intelligence to latency.

  13. · Business

    Coding agents picked sides. Compute drew the lines.

    OpenAI is pulling its models from SpaceX-owned Cursor while Anthropic, which rents $1.25 billion a month of SpaceX compute, promises Cursor more Claude, and the new X Subscription now prices every rival model as an extra.

  14. · Tools

    The AI skill gap is a verification gap, and it compounds

    Karpathy's capability funnel set off a week-long argument about skill, and the measured data from 718 firms, Anthropic's own telemetry and a randomized trial says the scarce skill is verifying output, built from the expertise heavy delegation stops producing.

In the data

Rows from the CC BY 4.0 datasets that these pieces report. Each links to its row, primary source and method.

Model releases · 10

Funding and acquisitions · 4

Key primary sources

More on this subject

Tag: coding-agents Tag: claude-code Tag: codex Tag: cursor Department: Tools Department: Agents All topic hubs