📖 Read the full version with all charts and screenshots on ComputeLeap →
On the morning of May 1, Sam Altman tweeted that "all of these 'which is better' polls are silly" and that developers should "use codex or claude code, whatever works best for you." The tweet pulled 15,300 likes and 818,000 views in a few hours.
That's not magnanimity. That's a posture. Market leaders do not need to defuse comparisons; challengers do. And the same morning Sam published the white-flag tweet, three things shipped that, taken together, explain what he was actually defending against — and what he was quietly winning.
-
OpenAI's Codex CLI 0.128.0 added
/goal— a native autonomous-loop primitive that runswhile True: agent.step()inside the CLI itself. - Cursor's SDK launched, exposing "the same runtime, harness, and models that power Cursor" as an embeddable agent substrate.
- GitHub trending was, simultaneously, dominated by personal-flavor agent-harness repos — five of the top fifteen, totaling +9,400 stars in 24 hours.
Read together, this is the surface war crystallizing. The harness layer — the while-loop wrapper around the API that a dozen YC-funded agent startups built businesses on — is being absorbed into the platform CLIs. What survives, and where ComputeLeap thinks the next 12 months of independent value lives, is the skills layer, the memory layer, and the tool-integration layer.
The /goal Primitive
Simon Willison's coverage of Codex CLI 0.128.0 cut to the chase in one line:
"Bad day for any startup whose moat was a while-loop around the API."
/goal collapses the agent-harness recipe into a one-liner inside the official OpenAI CLI:
codex /goal "Refactor the authentication module to use JWT, run the test suite, and open a PR"
That is the entire harness. No SDK. No agent framework. The loop, the tool registry, the retry logic, the completion check, the error recovery — all ship in the CLI.
The Cursor SDK Move
The same week Codex shipped /goal, Cursor shipped the Cursor SDK:
"Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor. Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products."
Read those announcements next to each other:
- OpenAI: the harness ships as a CLI primitive. Free.
- Cursor: the harness ships as embeddable runtime. Paid.
Both are saying the same thing in different price tiers: the harness is no longer where the value lives.
What's Actually Surviving
GitHub's trending board on May 1 had five agent-harness-adjacent repositories in the top fifteen, totaling +9,400 stars in 24 hours:
| Repo | +stars/24h | What it is |
|---|---|---|
mattpocock/skills |
+3,649 | Personal .claude directory, published as a product |
warpdotdev/warp |
+3,403 | "Agentic dev environment" rebrand of the terminal |
obra/superpowers |
+1,098 | Bundle of Claude Code skills + memory primitives |
Hmbown/DeepSeek-TUI |
+580 | Terminal-native coding agent specifically for DeepSeek |
Notice what is not on this list: a generic "agent framework." There is no AutoGen-clone trending today. No new LangGraph competitor.
What's trending is two patterns:
-
Personal-flavor skills bundles — the author's own
.claudedirectory, published. Product is the curation, not the runtime. - Model-specific harnesses — purpose-built for a single model family.
The category is fragmenting, not consolidating along the two axes platform CLIs cannot commoditize: personal taste, and model specificity.
The Polymarket Disagreement
Polymarket's Best AI Model end-of-May market prices:
- Anthropic: 80%
- Google: 16%
- OpenAI: 3% (down 15.8% on the week)
While dev Twitter reads "Sam's white flag + Codex /goal + Cursor SDK" as a coordinated OpenAI surface war, the most liquid prediction market on AI is pricing OpenAI's chance of holding the consensus-best model crown at three percent.
The trigger to watch: if Codex /goal adoption converts dev-channel attention into Polymarket movement within seven days, the thesis flips. If it doesn't, the divergence between narrative and pricing is itself the asymmetry.
TL;DR
OpenAI's /goal and Cursor's SDK both shipped this week, and both are saying the same thing: the harness is now substrate.
The five top harness-adjacent repos this morning are not generic frameworks — they are personal-flavor skills bundles and model-specific clients.
If you are still building a while-loop wrapper, this is your week to pivot. If you are building skills, memory, or deep integrations, this is your week to ship.
Originally published at ComputeLeap
Top comments (0)