tomsawyerhu/nano-harness/minimal-implementation-strategy

repair existing code: tests import project modules or source is close to correct
small replacement: expected behavior is narrow and can be implemented directly
wrapper/glue: existing project command/library already does most work
format/parser subset: hidden tests likely focus on common cases and edge formatting
build-only repair: behavior exists but compile/install path is broken

find . -maxdepth 2 -type f | sort | sed -n '1,120p'
find . -maxdepth 3 -type f \( -name '*test*' -o -name 'README*' -o -name 'compile.sh' -o -name 'Makefile' -o -name 'pyproject.toml' -o -name 'package.json' -o -name 'Cargo.toml' -o -name 'go.mod' \) -print

public API expected by tests
documented examples
existing executable/build target
language/runtime available in environment
data files or fixtures
hidden-test likely behavior

- tests import internal modules directly
- only one or two functions/classes are broken
- build already mostly works
- project has useful parser/formatter logic

- benchmark expects only ./executable behavior
- original project is large or expensive to build
- observed behavior is a small CLI subset
- standard library can implement the behavior

- a project binary or script already exists but compile.sh points wrong
- existing code handles the domain correctly
- the issue is path, permission, or invocation shape

- source behavior appears complete
- failure is missing executable, bad shebang, missing chmod, or wrong artifact path

Python standard library
POSIX shell/coreutils
existing project dependencies
single-file C/C++/Go/Rust only when toolchain is clearly present

implementation path:
files to change/create:
inputs handled:
outputs guaranteed:
known unsupported cases:
validation command: