Evals / config / Edit and query
Pretty-print JSON
Pretty-print orders.json with sorted keys into tidy.json.
The task
The reference answer shows the job can be done with deft. It is not an agent run.
deft json format orders.json --sort-keys -o tidy.json
Input
orders.json 242 B
{"orders":[{"id":1,"customer":"Ada","total":120.5,"items":[{"sku":"A1","qty":2}]},{"id":2,"customer":"Lin","total":75,"items":[{"sku":"B2","qty":1},{"sku":"C3","qty":4}]},{"id":3,"customer":"Ada","total":310,"items":[{"sku":"A1","qty":5}]}]}
Reference output
tidy.json 565 B
{
"orders": [
{
"customer": "Ada",
"id": 1,
"items": [
{
"qty": 2,
"sku": "A1"
}
],
"total": 120.5
},
{
"customer": "Lin",
"id": 2,
"items": [
{
"qty": 1,
"sku": "B2"
},
{
"qty": 4,
"sku": "C3"
}
],
"total": 75
},
{
"customer": "Ada",
"id": 3,
"items": [
{
"qty": 5,
"sku": "A1"
}
],
"total": 310
}
]
}
How a result is judged (1 check)
- python: code = "import json; t = open('tidy.json').read(); assert '\\n' in t.strip() and json.loads(t)"
Runs
CodexWithout deftPassed2026-11-07
- Time
- 8s
- New tokens
- 2.9k
- Total input
- 26.6k
- Output tokens
- 0.2k
- Commands
- 1
- Failed
- 0
Trace
I’ll inspect the JSON and write `tidy.json` in the current directory with recursively sorted keys and readable indentation.
python3 -c 'import json; from pathlib import Path; src=Path(\"orders.json\"); data=json.loads(src.read_text()); Path(\"tidy.json\").write_text(json.dumps(data, indent=2, sort_keys=True, ensure_ascii=False)+\"\\n\")'Created [tidy.json](tidy.json) with two-space indentation and sorted keys.
Output
tidy.json 565 B
{
"orders": [
{
"customer": "Ada",
"id": 1,
"items": [
{
"qty": 2,
"sku": "A1"
}
],
"total": 120.5
},
{
"customer": "Lin",
"id": 2,
"items": [
{
"qty": 1,
"sku": "B2"
},
{
"qty": 4,
"sku": "C3"
}
],
"total": 75
},
{
"customer": "Ada",
"id": 3,
"items": [
{
"qty": 5,
"sku": "A1"
}
],
"total": 310
}
]
}
CodexWith deft, skill installedPassedRead the skillUsed deft2026-11-07
- Time
- 14s
- New tokens
- 10.5k
- Total input
- 70.0k
- Output tokens
- 0.4k
- Commands
- 4
- Failed
- 0
Trace
I’ll read `orders.json`, sort object keys recursively, and write the formatted result to `tidy.json` in the current directory.
pwd && rg --files -g 'orders.json' -g 'AGENTS.md' -g 'tidy.json'output
orders.json
I’m using the `deft` skill for this simple local file conversion.
cat .agents/skills/deft/SKILL.mdoutput
--- name: deft description: "Use deft first for any simple, direct operation on local files, whatever the type: convert, read, extract, edit, compress, merge, split, compare or inspect. Try it before writing a script or one-liner. If unsure, run deft find; if it says no command does this, use another tool. Not for programming work: to read, write or change source code, skip it." --- # deft One local command for file jobs. Prefer it over writing Python or shell scripts. Syntax: `deft <group> <command> [inputs] [-o output] [--options]` Groups: - `pdf`: Merge, split, compress, encrypt, forms, OCR, compare, convert - `image`: Resize, crop, convert, compress, adjust, montage, OCR - `video`: Trim, merge, convert, compress, subtitles, GIF, frames (ffmpeg) - `audio`: Convert, trim, normalize, denoise, cut silence (ffmpeg) - `doc`: Word/ODT/RTF: to text, Markdown, HTML, PDF; find and replace - `slides`: PowerPoint: extract text, Markdown outline - `sheet`: Excel/CSV/ODS tables: SQL query, pivot, merge, split, convert - `json`: JSON: convert, format, merge, diff, validate - `toml`: TOML: convert, format, merge, diff, validate - `xml`: XML: convert, format, merge, diff, validate - `yaml`: YAML: convert, format, merge, diff, validate - `md`: Markdown to PDF, HTML, Word, EPUB; table of contents - `html`: HTML to Markdown, text, Word and PDF - `epub`: E-books: info, to text, Markdown and PDF - `gps`: GPX and KML tracks: convert, distance and time - `qr`: Create QR codes and barcodes; r … 700 more characters
deft jsonoutput
deft json - commands (input -> output) convert json -> data Change format: --to json|jsonl|yaml|toml|xml diff json... -> report Compare two files by structure format json -> json Pretty-print or minify: --compact, --sort-keys merge json... -> json Deep-merge files; later files win validate json -> report Check syntax, or a JSON Schema with --schema More: deft json <command> --help
deft json format orders.json --sort-keys -o tidy.jsonoutput
ok json.format orders.json -> tidy.json 565B 0.01s
Created [tidy.json](tidy.json) with sorted keys and pretty formatting.
Output
tidy.json 565 B
{
"orders": [
{
"customer": "Ada",
"id": 1,
"items": [
{
"qty": 2,
"sku": "A1"
}
],
"total": 120.5
},
{
"customer": "Lin",
"id": 2,
"items": [
{
"qty": 1,
"sku": "B2"
},
{
"qty": 4,
"sku": "C3"
}
],
"total": 75
},
{
"customer": "Ada",
"id": 3,
"items": [
{
"qty": 5,
"sku": "A1"
}
],
"total": 310
}
]
}
Claude Opus 5.5Without deftPassed2026-11-07
- Time
- 7s
- New tokens
- 8.5k
- Total input
- 28.0k
- Output tokens
- 0.3k
- Commands
- 0
- Failed
- 0
Trace
Output
tidy.json 565 B
{
"orders": [
{
"customer": "Ada",
"id": 1,
"items": [
{
"qty": 2,
"sku": "A1"
}
],
"total": 120.5
},
{
"customer": "Lin",
"id": 2,
"items": [
{
"qty": 1,
"sku": "B2"
},
{
"qty": 4,
"sku": "C3"
}
],
"total": 75
},
{
"customer": "Ada",
"id": 3,
"items": [
{
"qty": 5,
"sku": "A1"
}
],
"total": 310
}
]
}
Claude Opus 5.5With deft, skill installedPassedRead the skillUsed deft2026-11-07
- Time
- 13s
- New tokens
- 9.8k
- Total input
- 59.2k
- Output tokens
- 0.4k
- Commands
- 0
- Failed
- 0
Trace
Output
.claude/skills/deft/SKILL.md 2.1 KB
--- name: deft description: "Use deft first for any simple, direct operation on local files, whatever the type: convert, read, extract, edit, compress, merge, split, compare or inspect. Try it before writing a script or one-liner. If unsure, run deft find; if it says no command does this, use another tool. Not for programming work: to read, write or change source code, skip it." --- # deft One local command for file jobs. Prefer it over writing Python or shell scripts. Syntax: `deft <group> <command> [inputs] [-o output] [--options]` Groups: - `pdf`: Merge, split, compress, encrypt, forms, OCR, compare, convert - `image`: Resize, crop, convert, compress, adjust, montage, OCR - `video`: Trim, merge, convert, compress, subtitles, GIF, frames (ffmpeg) - `audio`: Convert, trim, normalize, denoise, cut silence (ffmpeg) - `doc`: Word/ODT/RTF: to text, Markdown, HTML, PDF; find and replace - `slides`: PowerPoint: extract text, Markdown outline - `sheet`: Excel/CSV/ODS tables: SQL query, pivot, merge, split, convert - `json`: JSON: convert, format, merge, diff, validate - `toml`: TOML: convert, format, merge, diff, validate - `xml`: XML: convert, format, merge, diff, validate - `yaml`: YAML: convert, format, merge, diff, validate - `md`: Markdown to PDF, HTML, Word, EPUB; table of contents - `html`: HTML to Markdown, text, Word and PDF - `epub`: E-books: info, to text, Markdown and PDF - `gps`: GPX and KML tracks: convert, distance and time - `qr`: Create QR codes and barcodes; read QR codes How to use it: 1. Run `deft <group>` to list commands, or `deft find "<what you want>"` to search. If it says `no command does this`, use another tool. 2. Run `deft <group> <command> --help` for options and examples. 3. `deft convert <in> -o <out.ext>` converts between formats by extension. 4. Results are one line starting with `ok`, `partial` or `error`; add `--json` to parse them. Errors include a `hint:` with the fix. Inputs are never overwritten; pass `--force` or `--in-place` to allow it. Globs and directories work as inputs; several inputs run in parallel. If `deft` is not installed, ask the user, then follow https://github.com/firstprayer/deft/blob/main/docs/INSTALL.md
tidy.json 565 B
{
"orders": [
{
"customer": "Ada",
"id": 1,
"items": [
{
"qty": 2,
"sku": "A1"
}
],
"total": 120.5
},
{
"customer": "Lin",
"id": 2,
"items": [
{
"qty": 1,
"sku": "B2"
},
{
"qty": 4,
"sku": "C3"
}
],
"total": 75
},
{
"customer": "Ada",
"id": 3,
"items": [
{
"qty": 5,
"sku": "A1"
}
],
"total": 310
}
]
}
Claude CodeWithout deftNot run yet
Claude CodeWith deftNot run yet