install

A command that installs craft-statusline as Claude Code’s active status line by updating `~/.claude/settings.json`. A status line is the information strip shown in the coding interface.

In plain words
What is it for?
Use it to activate craft-statusline, verify or replace an existing status line, and prepare the configuration file.
Why use it?
It sets up the status line while checking for the required `jq` tool and protecting an existing different status line unless you use `force`.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/derjochenmeyer/claude-code-craft-statusline/install
Clone the repo
git clone --depth 1 https://github.com/derjochenmeyer/claude-code-craft-statusline
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00837
Opus 5 $0.00008 $0.00418
Sonnet 5 $0.00003 $0.00167
Haiku 4.5 $0.00002 $0.00084

Measured 2d ago against content hash 48ab4ee1d384, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

install scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Debian: sudo apt install jq

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -F '${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/plugins/marketplaces/craft-statusline-marketplace}' ~/.claude/settings.json >/dev/null \
commands/install.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

craft-statusline:install

Install craft-statusline as the active status line.

Step 1: Check jq

command -v jq >/dev/null 2>&1 || echo "JQ_MISSING"

If JQ_MISSING, stop and show:

jq is required for craft-statusline (parses Claude Code's JSON input).
Install it:
  macOS:   brew install jq
  Debian:  sudo apt install jq
  Other:   https://jqlang.github.io/jq/download/

Then re-run /craft-statusline:install.

Do not proceed.

Step 2: Inspect existing statusLine

jq -r '.statusLine.command // "NONE"' ~/.claude/settings.json 2>/dev/null

Outcomes:

  • NONE, file missing, or statusLine absent. proceed to Step 3.
  • Output mentions craft-statusline.sh. already installed, jump to Step 4.
  • Anything else. report it and stop, unless $ARGUMENTS contains force:
    A different statusline script is already active:
      [current command]
    
    Run /craft-statusline:install force to replace it.
    

Step 3: Write settings.json

CRITICAL: Write the literal string ${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/plugins/marketplaces/craft-statusline-marketplace}/scripts/craft-statusline.sh into settings.json. Do NOT substitute the variable references with the expanded absolute path you may see in the rendered version of this skill. Both tokens must survive into the JSON verbatim so the line keeps working across plugin updates.

Pattern explained: Claude Code's statusline lives in settings.json outside the plugin system, so the statusline subprocess does not receive ${CLAUDE_PLUGIN_ROOT}. This is expected behaviour, not a bug, and was confirmed by Anthropic in anthropics/claude-code#52079 (closed as "expected existing behavior"). The POSIX default-expansion ${CLAUDE_PLUGIN_ROOT:-…} falls back to the marketplace clone path, which is version-stable. If Anthropic later integrates statusline into the plugin system, the same line will transparently pick up the official plugin root with no further action.

Read the full file on GitHub · 90 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 90 lines · 16 tokens per session scan C 48ab4ee1d384

Subscribe to this mod's changes

install is a command published in the GitHub repository derjochenmeyer/claude-code-craft-statusline (2 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 837 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.