Extract fields, filter records, and reshape JSON from API responses, configuration files, or logs using Crush’s built-in jq. Get help writing and debugging transformations, constructing new JSON, and formatting output for other commands.
Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.
Review the instructions the agent will receive before you install.
Crush ships a built-in jq command (via github.com/itchyny/gojq) available
in the bash tool. No external binary is required.
| Flag | Description |
|---|---|
-r, --raw-output | Output strings without quotes |
-j, --join-output | Like -r but no trailing newline |
-c, --compact-output | One-line JSON output |
-s, --slurp | Read all inputs into an array |
-n, --null-input | Use null as input (ignore stdin) |
-e, --exit-status | Exit 1 if last output is false or null |
-R, --raw-input | Read each line as a string, not JSON |
--arg name value | Bind $name to a string value |
--argjson name value | Bind $name to a parsed JSON value |
File arguments after the filter are also supported: jq '.foo' file.json.
The built-in uses gojq, which is a pure-Go jq implementation. Key differences:
keys_unsorted
and -S are unavailable."abcde"[2] returns "c".--ascii-output, --seq, --stream,
--stream-errors, -f/--from-file, --slurpfile, --rawfile,
--args, --jsonargs, input_line_number, $__loc__, some regex
features (backreferences, look-around).--yaml-input/--yaml-output but the
built-in does not currently expose these flags.Extract a field:
echo '{"name":"crush"}' | jq '.name'
Filter an array:
echo '[1,2,3,4,5]' | jq '[.[] | select(. > 3)]'
Reshape objects:
echo '{"first":"Ada","last":"Lovelace"}' | jq '{full: (.first + " " + .last)}'
Use variables:
echo '{}' | jq --arg host localhost --argjson port 8080 '{host: $host, port: $port}'
Slurp multiple JSON values:
echo '{"a":1}{"b":2}' | jq -s '.'
Compact output for piping:
echo '{"a":1}' | jq -c '.a += 1'
Raw string output:
echo '["one","two","three"]' | jq -r '.[]'
Process a file:
jq '.dependencies | keys' package.json
Null input for constructing JSON:
jq -n --arg msg hello '{"message": $msg}'
jq -r '.url' data.json | xargs curl| inside the expression, not shell pipes.try to suppress errors on missing keys: jq 'try .foo.bar'// "default" for fallback values: jq '.name // "unknown"'@csv, @tsv, @base64, @html, @uri for format strings.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Add or edit skills bundled with Crush, following guidance on file placement, required metadata, compile-time embedding, and discovery tests. It also explains how built-in skills are loaded and how user skills override them.
Configure Crush with Bash or JSON files to choose AI providers and models, connect external tools, set permissions, and adjust behavior. Understand how project and global settings combine when customizing your working environment.
Create, configure, and troubleshoot Crush hooks, commands that run before tool execution. Use them to block or approve calls, rewrite tool input, or add context for the agent, with guidance on configuration and troubleshooting.
Add or modify commands handled inside Crush's embedded shell before they reach the operating system. The guidance covers command routing, input and output streams, exit codes, and cancellation so commands work with pipes, redirection, and hook timeouts.