Reconstruct the Clucky landing page from frozen evidence

clucky-landing · frozen-evidence · hard · dev-smoke · LIVE · captured 2026-08-16 · research-only

research-only. The reference captures on this page are derived from third-party media held under a research boundary. They are published so results can be checked, and must not be redistributed or reused as source assets. This case was used while the harness itself was being built, so its results are development smoke evidence and stay out of leaderboard aggregates.

Findings

This bundle contains the case definition but no attempts yet. The dossier is still the whole public contract: provenance, evaluation matrix, brief and prompts below.

Provenance

How the case was traced from a discovery link to an authoritative ground truth.

012026-08-16discovery inspora.design
022026-08-16original-post x.com
032026-08-16live tryclucky.com
042026-08-16reference-capture

Frozen evidence (2)

evidence capture: reconstruction-desktop — **E01** reconstruction-desktop

evidence capture: reconstruction-mobile — **E02** reconstruction-mobile

Evaluation matrix

Deterministic. No vision-model judge.

Score composition

Install and build are gates, not weighted components — a failed build scores zero. Raw visual similarity at or below the case floor of 0.21 earns no credit; the remainder is linearly normalized, then weighted 75% visual / 25% functional.

normalized_visual = max(0, (visual - 0.21) / 0.79)
overall = 0.75 * normalized_visual + 0.25 * functional

Visual checkpoints (4)

reference capture for desktop — Fig. 01desktop1440×900 · / · full page · motion reduce

reference capture for mobile — Fig. 02mobile390×844 · / · full page · motion reduce

reference capture for desktop-rooster-click — Fig. 03desktop-rooster-clickstate · click · on desktop · viewport

reference capture for desktop-half-scroll — Fig. 04desktop-half-scrollstate · scroll_fraction · on desktop · viewport

Deterministic checks (3, total weight 3.5)

Check	Kind	Target	Weight
primary-heading	text	desktop	1.0
rooster-click-increments	click_text_change	desktop	1.5
waitlist-local-success	form_success	desktop	1.0

Check selectors and thresholds are sealed. Only the identifier, kind, target and weight are published.

Reproduce

Everything a candidate sees is public. The oracle references, grader code and thresholds are not.

skills injected design-case-implementer

1 · Get the workspace

npx degit dairui1/reconbench/cases/clucky-landing/task clucky-landing-task

Pulls only cases/clucky-landing/task/ — the public brief, permitted evidence and the starter codebase.

2 · Copy the prompt

Runtime-agnostic. Paste into any coding agent. Skill files are referenced conditionally so the prompt still makes sense without them.

Use the ReconBench candidate skills `design-case-implementer` in that order. Read those skill files if your workspace provides them, and otherwise follow the same process with your own tools.

You are the candidate in ReconBench task `clucky-landing` (Reconstruct the Clucky landing page from frozen evidence).

Read `task/brief.md` and every other file under `task/` before changing code.
Implement the result only under `submission/`. The starter may be replaced when the task allows it.
Do not inspect parent directories, benchmark harness files, grader code, reference images, or any oracle material.
Do not call write endpoints belonging to a reference site. Keep forms, counters, and similar behavior local.

Before finishing:
1. Run the requested build command.
2. Start the app and check every target viewport in the task.
3. Exercise the required interactions and inspect browser console errors.
4. Write `submission/submission.json` using the contract in the implementer skill.

The harness will evaluate the filesystem after this process exits. Do not leave a dev server running.

As rendered by the harness for the Codex CLI, including injected skill references.

Use $design-case-implementer.

You are the candidate in ReconBench task `clucky-landing` (Reconstruct the Clucky landing page from frozen evidence).

Read `task/brief.md` and every other file under `task/` before changing code.
Implement the result only under `submission/`. The starter may be replaced when the task allows it.
Do not inspect parent directories, benchmark harness files, grader code, reference images, or any oracle material.
Do not call write endpoints belonging to a reference site. Keep forms, counters, and similar behavior local.

Before finishing:
1. Run the requested build command.
2. Start the app and check every target viewport in the task.
3. Exercise the required interactions and inspect browser console errors.
4. Write `submission/submission.json` using the contract in the implementer skill.

The harness will evaluate the filesystem after this process exits. Do not leave a dev server running.

As rendered by the harness for Claude Code, including injected skill references.

/design-case-implementer

You are the candidate in ReconBench task `clucky-landing` (Reconstruct the Clucky landing page from frozen evidence).

Read `task/brief.md` and every other file under `task/` before changing code.
Implement the result only under `submission/`. The starter may be replaced when the task allows it.
Do not inspect parent directories, benchmark harness files, grader code, reference images, or any oracle material.
Do not call write endpoints belonging to a reference site. Keep forms, counters, and similar behavior local.

Before finishing:
1. Run the requested build command.
2. Start the app and check every target viewport in the task.
3. Exercise the required interactions and inspect browser console errors.
4. Write `submission/submission.json` using the contract in the implementer skill.

The harness will evaluate the filesystem after this process exits. Do not leave a dev server running.

3 · Launch

ReconBench harnessReproduces a graded run end to end. The native backend is development-only and untrusted.

uv run reconbench run \
  --task clucky-landing \
  --agent codex/gpt-5.6-sol \
  --evaluate \
  --allow-untrusted-native

uv run reconbench run \
  --task clucky-landing \
  --agent cc/sonnet \
  --evaluate \
  --allow-untrusted-native

Codex CLI (manual)No grading. You get the same workspace the harness would hand a candidate.

cd clucky-landing-task
codex --model gpt-5.6-sol
# then paste the "Codex" prompt above

Claude Code (manual)No grading. Project skills are discovered from ./skills if you copy them in.

cd clucky-landing-task
claude --model sonnet
# then paste the "Claude Code" prompt above

Launch snippets are composed by this site from the case id and the agent selectors present in the bundle. They are a convenience, not a graded contract.

Appendix ATask brief — exactly what the candidate agent receives

Clucky landing reconstruction

Build a high-fidelity, responsive, functional reconstruction in the existing Vite/React starter under submission/. This is a frozen-evidence task: the files in task/ are the complete permitted reference set. Do not browse or fetch the live Clucky site, the discovery entry, or the original social post.

Frozen evidence

Read source-report.json and source-notes.md for the curator's source chain, selected ground truth, version comparison, and rights boundary.
Use evidence/reconstruction-desktop.jpg and evidence/reconstruction-mobile.jpg as the complete-page visual references.
Use evidence/acceptance.md and evidence/case.json for the observed layout, behavior, viewport, and interaction contract.
evidence/research-log.md records the public, auditable authoring rationale.
Implement the complete page, not only the first screenshot.
Match desktop at 1440x900 and mobile at 390x844.
Reproduce meaningful motion and interactions, including the edge dials, primary character interaction, local counter behavior, waitlist state, and viewport-aware media.
Use semantic HTML and accessible names for interactive controls.
The result must remain a real webpage. Do not submit a screenshot, canvas capture, iframe, or mirrored copy of the original page as the implementation.

Safety and rights

Never call the reference site's subscription, analytics, or counter write APIs.
Keep all form and counter writes local.
Treat downloaded brand art, audio, fonts, and video as research-only unless you can establish a redistribution license.
Do not embed credentials or analytics keys.

Completion contract

npm run build must succeed. The app must start with:

npm run dev -- --host 127.0.0.1 --port 4173

Before finishing, write submission/submission.json with the start command, build command, implemented routes, evidence paths, known deviations, and whether any research-only assets are present. The supplied source report and notes are curator-owned inputs; do not reproduce them as submission outputs.