Agent skill

JSON Processing with jq

by charmbracelet in charmbracelet/crush

Explains the jq command built into Crush for querying, filtering and reshaping JSON, including its supported flags and where it differs from standard jq.

Custom licenceAuto-check passedDevelopment

Install JSON Processing with jq

skills CLI
$ npx skills add charmbracelet/crush --skill jq -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install charmbracelet/crush jq --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/charmbracelet/crush.git skills-src && mkdir -p .claude/skills && cp -r skills-src/internal/skills/builtin/jq .claude/skills/jq && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
jq
GitHub stars
29k
Token cost
~746 tokens
SKILL.md length
273 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
Custom licence

At a glance

Explains the jq command built into Crush for querying, filtering and reshaping JSON, including its supported flags and where it differs from standard jq.

  • Pulling fields out of an API response or log line
  • SKILL.md covers Supported Flags, Differences from Standard jq, Common Patterns and Tips
  • Calls jq
  • Reshaping a JSON config into a different structure

What it does

Crush ships `jq` inside its bash tool, built on the pure-Go gojq library, so no external binary is needed. The skill lists the supported flags (raw and compact output, slurp, null input, exit status, raw input, `--arg` and `--argjson`) and notes that file arguments after the filter work as usual. Worked patterns cover extracting a field, filtering an array, reshaping objects, binding variables, slurping several values and building JSON from nothing with `-n`.

Because the engine is gojq, a few behaviors differ from standard jq: object keys are always sorted, large integers keep full precision, and strings can be indexed. Options such as `--stream`, `--seq`, `--from-file`, `--slurpfile`, `--rawfile` and `--args`, plus some regex features like look-around, are not available, and the YAML flags are not exposed.

When your agent uses it

  • Pulling fields out of an API response or log line
  • Reshaping a JSON config into a different structure
  • Debugging a jq filter that behaves differently from standard jq

Example prompts

  • “List every dependency name in package.json using jq.”
  • “Turn this array of users into an object keyed by email address.”
  • “Build a JSON payload from a host and port without hand-quoting it.”

Requirements

  • Crush's bash tool, which includes jq

What it can do on your machine

Read from SKILL.md and the folder at commit 140e8cb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

JSON Processing with jq loads about 746 tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 273 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~746

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 273 words (~746 tokens).

“Crush ships a built-in jq command (via github.com/itchyny/gojq) available in the bash tool. No external binary is required.”

— opening of SKILL.md by charmbracelet, Custom licence
name
jq

Read the full SKILL.md on GitHub

Files

Just SKILL.md in internal/skills/builtin/jq of charmbracelet/crush.

Open the folder on GitHubat commit 140e8cb

Compare with similar skills

JSON Processing with jq next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

JSON Processing with jq compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
JSON Processing with jq this skillcharmbracelet/crush29k—~746Automated safety check: PassCustom licence
Mole Bug Patternstw93/Mole70k—~2kAutomated safety check: PassGPL-3.0
CLI DeveloperJeffallan/claude-skills12k2 repos~1.2kAutomated safety check: PassMIT
Shellm Architecture Referencelaude-institute/headlong1.2k—~2kAutomated safety check: NotesApache-2.0
Bash Scriptingpromovaweb/setupvibe1015 repos~1.2kAutomated safety check: PassGPL-3.0
Cppcrazyguitar/cppcheatsheet290—~1.8kAutomated safety check: PassMIT

Similar skills

  • A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.

    70k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • CLI Developer

    Jeffallan/claude-skills

    Walks through designing, building and polishing a command-line tool: user workflow and command hierarchy, implementation in commander, click, typer or cobra, completions and cross-platform testing.

    12k GitHub starsUsed in 2 repos~1.2k tokens
    DevelopmentAuto-check passed
  • Shellm Architecture Reference

    laude-institute/headlong

    Explains how shellm's bash-based recursive LLM shell fits together - its core engine, identity system, memory, skills and trajectory log.

    1.2k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Bash Scripting

    promovaweb/setupvibe

    Bash scripting workflow for creating production-ready shell scripts with defensive patterns, error handling, and testing.

    101 GitHub starsUsed in 5 repos~1.2k tokens
    DevelopmentAuto-check passed
  • Cpp

    crazyguitar/cppcheatsheet

    Comprehensive C/C++ programming reference covering everything from C11-C23 and C++11-C++23, system programming, CUDA GPU computing, debugging tools, Rust interop, and advanced topics.

    290 GitHub stars~1.8k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Bash Pro

    promovaweb/setupvibe

    Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities.

    101 GitHub starsUsed in 11 repos~4.7k tokens
    DevelopmentAuto-check passed

More from charmbracelet/crush

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated yesterday
    Auto-check passed
  • Crush Hook Writer

    charmbracelet/crush

    Helps write, debug and configure Crush hooks in crush.json that block, approve or rewrite tool calls before they run.

    29k GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed
  • Crush Shell Builtins

    charmbracelet/crush

    Explains how to add a new in-process builtin command to Crush's embedded POSIX shell, so it is intercepted before reaching the OS, with context polling and exit-status rules.

    29k GitHub stars~790 tokensUpdated yesterday
    Auto-check passed
  • Crush Builtin Skills

    charmbracelet/crush

    Explains how the Crush coding agent embeds builtin skills in its binary and how to add or edit one, including the discovery test and build commands.

    29k GitHub stars~466 tokensUpdated yesterday
    Auto-check passed

Works with

Questions about JSON Processing with jq

What does JSON Processing with jq do?

Explains the jq command built into Crush for querying, filtering and reshaping JSON, including its supported flags and where it differs from standard jq. Crush ships `jq` inside its bash tool, built on the pure-Go gojq library, so no external binary is needed. The skill lists the supported flags (raw and compact output, slurp, null input, exit status, raw input, `--arg` and `--argjson`) and notes that file arguments after the filter work as usual.

When should I use JSON Processing with jq?

JSON Processing with jq fits situations like: pulling fields out of an API response or log line; reshaping a JSON config into a different structure; debugging a jq filter that behaves differently from standard jq.

How do I install JSON Processing with jq in Claude Code?

Run `npx skills add charmbracelet/crush --skill jq -a claude-code`. Or copy the skill folder (internal/skills/builtin/jq in charmbracelet/crush) into .claude/skills/jq in your project. Claude Code loads it when a task matches its description.

How do I install JSON Processing with jq in Codex?

Run `npx skills add charmbracelet/crush --skill jq -a codex`. Or copy the skill folder (internal/skills/builtin/jq in charmbracelet/crush) into .agents/skills/jq in your project. Codex loads it when a task matches its description.

Can I use JSON Processing with jq in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add charmbracelet/crush --skill jq -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jq, .gemini/skills/jq, .github/skills/jq and .opencode/skills/jq in your project.

What does JSON Processing with jq need to run?

Going by SKILL.md and its folder, JSON Processing with jq needs the command-line tools its instructions call (jq). Our summary lists: Crush's bash tool, which includes jq.

Does JSON Processing with jq access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is JSON Processing with jq safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does JSON Processing with jq use?

JSON Processing with jq has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does JSON Processing with jq use?

About 746 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to JSON Processing with jq?

Skills that share tags, products or a category with JSON Processing with jq: Mole Bug Patterns (tw93/Mole, 70k stars), CLI Developer (Jeffallan/claude-skills, 12k stars), Shellm Architecture Reference (laude-institute/headlong, 1.2k stars) and Bash Scripting (promovaweb/setupvibe, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains JSON Processing with jq?

charmbracelet (a GitHub organization) maintains it in charmbracelet/crush, which has 28,533 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.

Source: charmbracelet/crush on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.