Threadlines v0.5.0 is out 🧵 Rooms: more than one coding agent in a thread. Ask Codex while Claude works, or have them review each other. Also new: Cursor and fx support. Free and open source. Release notes: github.com/Threadlines/threa…

An agent that can push straight to main will do it eventually. On a Friday.

I use Claude Code and Codex every day and still switch depending on the job. What makes you pick one?

A small one from v0.4.1. When an update is ready, the version label next to Settings turns into an Update button. One click downloads it. Restart still asks first, because restarting stops any agents that are running.

Me at 9am: I'll read every line the agent writes. Me at 4pm: LGTM

Anthropic has launched Claude Sonnet 5.5: it scores 56 on the Artificial Analysis Intelligence Index, just 2 points behind Opus 5.5 (max), but at the highest Output Tokens per Task we’ve seen With max effort, Sonnet 5.5 gains 18 points over Sonnet 5 and to #2 on the Intelligence Index behind only Opus 5.5 (max). Anthropic has priced Sonnet 5.5 identically to Sonnet 5 at $0.2/$2/$10 per 1M cache input/input/output tokens, however it outputs a higher number of Output Tokens per Task and costs $7.60 per task (~50% higher than Sonnet 5’s Cost per Task) Key takeaways: ➤ Meets leading models on agentic terminal use and knowledge work: in Terminal-Bench 4.0, Claude Sonnet 5.5 reaches 64% against 60% for Opus 5.5 and GPT-6 Astra. On AA-Briefcase (1811 vs 1822 Elo), GDPval-AA (1844 vs 1846 Elo), and AutomationBench-AA (71% vs 70% headline score), Sonnet 5.5 reaches parity with Opus 5.5, albeit with significantly higher token usage to achieve it ➤ Heaviest token use we have measured: at max effort, where it reaches performance nearing that of Opus 5.5, Claude Sonnet 5.5 used ~193k Output Tokens per Intelligence Index Task. This is the highest token use we have measured on around 60% higher than Opus 5.5 (max) or Sonnet 5 (max) and ~7x GPT-6 Astra (max) ➤ Pricing remains at $2/$10 per million tokens of input/output, matching GPT-6 Sol. At this pricing Claude Sonnet 5.5 sits off the Intelligence vs. Cost per Task Pareto Frontier. At high effort levels it sits behind Opus 5.5, while lower efforts have GPT-6 Astra or Sol configurations delivering equivalent performance for lower cost. The high effort setting is the most competitive on this basis, sitting very narrowly behind GPT-6 Sol on Intelligence at effectively the same Cost per Task ➤ Behind Opus 5.5 on factual knowledge and scientific reasoning: as a smaller class model, Sonnet 5.5 still lags on factual knowledge in AA-Omniscience compared to Opus 5.5. It scores 54% against 66% for factual accuracy, though with a lower hallucination rate (47% against 59%). It also sits ~6 points lower on Humanity's Last Exam and SciCode compared to Opus These evaluations were conducted on a pre-release deployment of Claude Sonnet 5.5, which Anthropic found to have a bug that can degrade responses to requests that use structured outputs. This is fixed for the public release and Anthropic expects minimal change or slightly understated performance, but we will be re-running relevant evaluations soon. Other model details: ➤ Context window: 1 million tokens with image and text input, unchanged from Sonnet 5 ➤ Pricing: unchanged from Sonnet 5’s latest $2/$10 per 1M input/output tokens; cache writes at $2.5, cache reads $0.2 ➤ Effort settings: five (low, medium, high, xhigh, max). Intelligence Index evaluations were run at all five with Anthropic's default fallback enabled. We see Sonnet 5.5 fall back in ~0.1% of tasks across the Intelligence Index, primarily in TerminalBench 4.0, falling back to Sonnet 5 in all cases.

Usage meters in Threadlines now turn amber at 75% and go red as you near your limit, for Codex and Claude. You see the limit coming before a turn stops. What time of day do you usually hit yours?

Stop babysitting CI just to press merge. Open the PR popup above the message box and turn on Merge when checks pass. If the repo has GitHub auto-merge turned off, Threadlines waits for the checks and does the merge itself while the app is running. threadlines.dev/download

Opus 5.5 is the first Opus I don't ration. I usually cap my models at High reasoning. I've been running this one on Max, and it still barely dents my usage. It's in the Threadlines model picker now. You'll need Claude Code 2.1.280 or newer. How's it been for you so far?

Threadlines v0.4.1 is out 🧵 • Claude Opus 5.5 in the model picker • Merge a PR once its checks pass • Usage meters turn red near your limit • Codex 0.155 support Free and open source. Release notes: github.com/Threadlines/threa…

They cooked with Opus 5.5

Ladies and gentlemen... start... your... ENGINES. We are almost Tuesday and I promised a reset for Tuesday. Among some other things. See you soon.

Codex and Claude Code, with the work around them. Keep active threads, pull requests, and code review together in Threadlines. Free and open source. threadlines.dev/download

First run should tell you what to do next. Threadlines checks your coding agents and Git tools, shows what needs installing or signing in, and gets you to your first thread. You only need one agent ready to begin. threadlines.dev/download

Follow a GitHub PR from running checks to the next fix in Threadlines. Open the PR page, inspect a failed check, and add its context straight to the agent composer. Demo check states shown. threadlines.dev/download

Threadlines v0.4.0 is out 🧵 • GitHub PR review and check handoff • Optional PR auto-fix • English dictation • Better first-run setup Free and open source. Release notes: github.com/Threadlines/threa…

Might be a little too proud of our Git graph. A lot of PRs have gone into Threadlines, and I love seeing the work add up. We're building a home for coding agents, with your threads, diffs, and Git history in one place. threadlines.dev

We will give one banked reset for every day you don't have access to Astra on your paid ChatGPT plan, starting today. Team is moving mountains to give access as fast as we can. First one will land in ~ 3 hours. There is still time to create your account if you don't have one.

Threadlines v0.3.8 is out 🧵 • Claude Fable 5.1 in the picker • Message Codex subagents directly • Background agents shown in roster • Browser preview find and page errors • Codex CLI 0.150 support Release notes: github.com/Threadlines/threa…

With Fable 5.1 out today, we've also reset 5-hour and weekly limits for all users.