Ranked by what each change is worth on the composite — the gap to the next rung of the ladder times the dimension’s weight. Computed from the scores, not written by the model; the model’s sentence under each is the action.
Use a concrete product noun in the headline (e.g., a specific coding tool or workflow) to clarify what is sold.
Use plain language for core actions (e.g., 'view', 'monitor', 'start' the agent) instead of multi-step terms like 'Review Opens' or 'Take over'.
Include a named user or organization with a quantified result (e.g., 'Jordan’s Mac Studio reduced review time by X').
All three together: 53 → 63. Every dimension one rung up: 63 (grade C). Ceiling is 95.
Built only from facts already on the page — not the company’s words. Shown so the gap between what was written and what could have been written is concrete rather than a number.
Five alternative headlines in five angles, a subhead, a call-to-action line, and a line-by-line edit for each of the five dimensions — written only from facts already on codeconnect.sh, gated like a rating (anything with a struck word is dropped, not sold). Delivered on a private page in about a minute.
Five dimensions on one ladder — 5 · 20 · 35 · 50 · 65 · 80 · 95 — weighted clarity 30%, specificity 20%, jargon 20%, proof 15%, call to action 15%. For each: the rung the page matched, the words that drove it, and what would reach the next rung. Full rubric →
The headline does not name a concrete product category in plain words.
CodeConnect - Every coding agent, at a glance
Next rungUse a concrete product noun in the headline (e.g., a specific coding tool or workflow) to clarify what is sold.
The page includes multiple numbered items describing status and risk, tied to outcomes.
4 waiting for you 5 agents · 1 done · 1 running
Heavy domain terms (agent, tailnet, session, diffs) reduce clarity for non-experts.
Scored from the page as a whole; no single line was cited.
Next rungUse plain language for core actions (e.g., 'view', 'monitor', 'start' the agent) instead of multi-step terms like 'Review Opens' or 'Take over'.
No named customers or verifiable metrics about external users or deployments.
Nothing on the page addresses this.
Next rungInclude a named user or organization with a quantified result (e.g., 'Jordan’s Mac Studio reduced review time by X').
Clear primary action to download the app is present, matching the promise to view and manage agents.
Download CodeConnect Remote on the App Store
Download CodeConnect Remote on the App StoreDirect CTA that aligns with a download action.
Projects is the app’s home screen. Every session from every paired computer is on itSupports clarity but uses abstract 'app' and 'session' terminology.
CodeConnect - Every coding agent, at a glance Every coding agent, at a glance. Claude Code and Codex, running on your Mac or your Linux machines, on one screen in your pocket. See what each one is doing, and answer the one it is waiting on. Download CodeConnect Remote on the App Store Free for iPhone. Then one command on your computer. Your tailnet Your iPhone On cellular · 100.88.14.62 4 waiting for you 5 agents · 1 done · 1 running Jordan’s Mac Studio Live macOS · 100.101.7.12 app-1 Bash git push --force origin main Claude Code High 1m04s app-2 Edit …/Sources/Router.swift Claude Code · +1 more Medium 4m04s app-3 Read …/README.md Claude Code 5m04s app-4 Command output Codex · done 3s app-5 Bash ./soak/run.sh --pass 8 Claude Code · running 2s build-server-eu-west-1 Offline Linux · 100.72.40.9 Everything waiting on you, counted and ranked. Projects is the app’s home screen. Every session from every paired computer is on it, and the ones stopped on you come first. The app 4 waiting for you How many agents are stopped, waiting on you. Jordan’s Mac Studio Each project names the computer it runs on. Bash git push --force What it is waiting on, how risky, and for how long. 1 HIGH · 2 MEDIUM · 1 LOW The risk of everything waiting, counted. Review Opens everything waiting for you, riskiest first. The whole command, and nothing decides but you. When an agent needs a yes, your phone shows the exact command, never shortened or faded, with what it does and how risky it is. A read is one
Strongest: Specificity 95. Weakest: Proof 5. The 4 passes disagreed by 23 points, so treat this score as contested. The band 41–65 is where a re-score of this unchanged page would most likely land: on 42 dry re-scores (12 Oct 2026) the median move was 6 points and one in four moved more than 10. A grade only changes when a new score clears the boundary by 5.
No word in the headline itself was judged empty, yet jargon-free scores 65: the scorer found generic phrasing further down the page. Heavy domain terms (agent, tailnet, session, diffs) reduce clarity for non-experts.
Badges are issued to grades A and B. The share card for this page shows the headline with its jargon struck through; paste the URL anywhere that unfurls links.
Scored from the live homepage
on 2026-11-01 by gpt-5-nano,
4 independent passes, median taken.
Page snapshot 12059fce01b8.
Rubric 7329c240 (current; what it says).
No person reviewed or edited this score. If the rubric and the score disagree, the rubric wins
and the page is re-scored — not hand-corrected.
Re-scored when the homepage text changes.