abi / screenshot-to-code

GitHub

Code

How abi/screenshot-to-code is laid out, and where to start for common changes.

Architecture grade

score 99/100

Import cycles

lower is better

246

Files mapped

223 imports between them

98%

Layering

of imports point one way

From the map of which files import which, built when the code was last read in full. It shows what depends on what, not a reading order.

Module map

Shade by

14 modules, 28 links. A link means one module imports another; thicker lines mean more imports. Select a module to trace it: blue lines go to what it uses, orange lines come from what uses it.

Where to start reading

Repository root
Repository root
Likely public API
Likely public API
Likely start-up file
Likely start-up file
Suggested starting pointAI
Suggested starting pointAI

Find files for a task

Add a new LLM provider

Register provider in factory's instantiation logic
Add provider-specific configuration and API keys to environment
Test with existing evaluation suite

Add a new supported code stack (e.g., new CSS framework)

Add stack template and output format rules
Update code generation pipeline with stack-specific formatting
Add stack option to frontend UI component
Test with evaluation benchmark

Add a new API endpoint for screenshot processing

Wire route into pipeline via agent engine or direct code generation
Add WebSocket event constants if real-time updates needed

Improve code generation quality via prompt engineering

Examine and modify the message building logic
Refine design system prompt injections
Run evaluation suite to measure improvement
Document changes in design docs if architectural

Change the public API

Trace runtime behavior

Add or update tests

Change build or automation

RepoPilot lists up to 500 files, so a file missing here may still exist.

Files marked “likely” are guessed from their names.

Code quality and hotspots

Largest source files

Branch points68 per file on average
Code issues0 errors, 22 warnings
Largest file1,124 lines
Hotspot load4 high-risk files

Static checks on the 15 largest source files.

Tests, CI and tooling

CINot detected
Tests53 test filesPytest · 0.26 test files per source file (file count, not coverage)
Dependency updatesNo config detected

Test folders: backend/tests · backend/codegen

Hotspots

frontend/src/App.tsx14 commits in 180 days · 98 branch points
frontend/src/components/sidebar/Sidebar.tsx11 commits in 180 days · 102 branch points
backend/agent/tools/runtime.py16 commits in 180 days · 18 branch points
frontend/src/components/agent/AgentActivity.tsx8 commits in 180 days · 234 branch points
backend/routes/generate_code.py8 commits in 180 days · 30 branch points
backend/agent/providers/anthropic/provider.py14 commits in 180 days · 17 branch points
backend/agent/providers/openai.py9 commits in 180 days · 17 branch points
backend/fs_logging/agent_runs.py4 commits in 180 days · 38 branch points

Files that change often and branch heavily, highest first. Branch points count if, loop, case, catch, ternary, && and || in the file.