Skip to main content
skill CX Codex

statusline-generator — Claude Code skill: a statusline that proves it

Installs and repairs the Claude statusline: path, git branch, model and token counts. It also checks that the script actually runs.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add daymade/claude-code-skills --skill statusline-generator -a claude-code
Open on GitHub

What statusline-generator does

The skill builds the statusline from a single script and verifies it end to end. The install script copies generate_statusline.sh to ~/.claude/statusline.sh, sets the executable bit, and updates the statusLine block in ~/.claude/settings.json with jq, leaving your other settings alone. Existing files get backed up first.

Two layouts. The default is one line: short path, branch, model name, absolute token counts. The branch comes from reading .git/HEAD as a plain file instead of spawning git, so it works on hosts without a git binary. Set CLAUDE_STATUSLINE_LAYOUT=full in your shell profile for the multi-line version: user, ccusage costs, a colour-coded context percentage, and a git line marking modified and untracked files.

The usual reason a statusline goes blank is a script without chmod +x. Claude calls it, exec fails silently, nothing renders. So health_check.sh validates four layers, the executable bit among them, and prints a ready fix command for each failure. Run it first when the bar disappears or freezes. One more thing worth knowing: the statusline runs on every refresh in every live session, so heavy subprocesses there add up — this script spends one jq and one awk, and only the full layout calls git status. Field-level traps such as used_percentage being null at session start are covered in references/context-window-schema.md.

What it helps with

  • set up a statusline from scratch without missing the executable bit
  • fix a blank or frozen statusline
  • switch from the minimal layout to the full one with cost tracking
  • show absolute token counts instead of a percentage
  • capture the JSON Claude pipes into the script

Example prompts for the agent

  • Install statusline-generator and set up my statusline
  • My statusline is blank — run health_check.sh and fix it
  • Switch the statusline to the full layout with ccusage costs

How to install statusline-generator

1Skills CLI (Vercel)

npx skills add daymade/claude-code-skills --skill statusline-generator -a claude-code

2Manually: put the files in place

~/.claude/skills/statusline-generator/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/statusline-generator/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about statusline-generator

How do I install statusline-generator in Claude?

Run npx skills add daymade/claude-code-skills --skill statusline-generator -a claude-code. The skill then runs scripts/install_statusline.sh, which always finishes by running scripts/health_check.sh. Restart Claude or send a new message to see the statusline.

What does statusline-generator do?

It installs, configures and troubleshoots the Claude statusline: working directory, git branch, model and token counts. It can switch between the minimal and full layouts and add cost tracking through ccusage.

Why is my statusline blank?

Most often ~/.claude/statusline.sh is missing its executable bit, so Claude's exec fails silently and nothing renders. bash scripts/health_check.sh catches that and prints the fix command.

Source text

SKILL.md · MIT
---
name: statusline-generator
disable-model-invocation: true
description: >-
  Installs, configures, customizes, or troubleshoots the Claude Code statusline (cwd, model, token
  counts). Use when the user wants to set up or change the statusline, switch minimal vs full
  layouts, show absolute token counts instead of a percentage, add cost via ccusage, or fix a
  statusline that is blank, silent, stuck, or stopped updating. Trigger phrases: 状态栏, 状态栏不显示, 状态栏空白,
  "statusline blank", "statusline broken".
---

# Statusline Generator

A single-source-of-truth statusline for Claude Code. One script, two layouts,
end-to-end self-verification.

## Quick health check (start here when something is wrong)

Run this first whenever the statusline misbehaves. It catches the silent failures
that account for most "configured but not working" reports:

```bash
bash scripts/health_check.sh
```

It validates four layers:
1. `~/.claude/statusline.sh` exists and is executable. **Missing `chmod +x` is
   the single most common silent-failure cause** — Claude Code runs the script,
   `exec` fails, statusline goes blank.
2. `~/.claude/settings.json` has a valid `statusLine` block pointing at the script.
3. Mock stdin tests covering complete data, zero tokens, missing fields,
   `$HOME` path shortening, and zero-fork git-branch rendering (via a synthetic
   `.git/HEAD` — no git binary required).
4. Real stdin replay from `/tmp/.claude-statusline-last-stdin.json` if you
   previously ran with `CLAUDE_STATUSLINE_DEBUG=1`.

Each failure prints a one-line fix command — you don't have to read documentation
to recover.

## Quick install

```bash
bash scripts/install_statusline.sh
```

This script:
- Backs up any existing `~/.claude/statusline.sh` and `settings.json`.
- Copies `generate_statusline.sh` to `~/.claude/statusline.sh` and `chmod +x`s it.
- Updates `settings.json` `statusLine` block via `jq` (preserves other settings).
- **Mandatorily runs `health_check.sh` and shows the result** — installation
  is not "complete" until verification passes.

Restart Claude Code (or send any new message) to see the statusline update.

## What you get

### Default — minimal one-line layout

```
~/code/myproject  [main]  Opus 4.7 (1M context)  ctx: 108K / 1M
```

Just the essentials: short path, git branch, model name, absolute token counts.
No colors, no cost, no percentage. The branch is read **zero-fork** — the script
reads `.git/HEAD` as a plain file (with worktree/submodule `gitdir:` indirection
and detached-HEAD short-sha handling) instead of spawning `git`, so it costs
nothing and works even on hosts without a git binary.

### Full — multi-line with cost and git

Set `CLAUDE_STATUSLINE_LAYOUT=full` in your shell profile to enable:

```
alex (Sonnet 4.6) [$0.42/$25.93]  ctx: 108K/1M (11%)
~/code/myproject
[git:main*+]
```

- Line 1: user, model, ccusage session/daily costs, color-coded ctx (green ≤50%,
  yellow 51–80%, red >80%).
- Line 2: short path.
- Line 3: git branch with `*` for modified, `+` for untracked.

## Layouts: how to switch

The script reads layout from environment, not flags (Claude Code passes JSON on stdin,
so flags would conflict). Set in `~/.zshrc` or `~/.bashrc`:

```bash
# Minimal (default — same as not setting it)
export CLAUDE_STATUSLINE_LAYOUT=minimal

# Full
export CLAUDE_STATUSLINE_LAYOUT=full
```

Restart your shell (or `source` the rc file) so Claude Code inherits the change,
then send a message — statusline refreshes within 300ms.

## Debug stdin capture

To see exactly what JSON Claude Code sends your script:

```bash
export CLAUDE_STATUSLINE_DEBUG=1
```

Each invocation writes its stdin to `/tmp/.claude-statusline-last-stdin.json`
(overwriting on every refresh). Inspect with `jq .`. Useful for:

- Diagnosing why a field doesn't render the way you expect.
- Re-running the script against real input: `cat /tmp/.claude-statusline-last-stdin.json | ~/.claude/statusline.sh`.
- Filing bug reports — paste the dump as ground truth.

## Authoring rules (why this skill is shaped this way)

Three production failure modes drove the current design. All are sealed in code,
not just docs:

### Rule 1 — Always `chmod +x`, always verify by running

The single biggest silent-failure cause of any statusline is a script without
the executable bit: Claude Code's `exec` fails silently and the bar goes blank
with no error. `install_statusline.sh` always `chmod +x`s; `health_check.sh`
flags the bit if missing. **If you hand-write or hand-edit a statusline script,
mock-test it before declaring done:** `echo '{}' | bash your-script.sh`.

### Rule 2 — "Configuration complete" is meaningless without evidence

"Wrote the file and updated settings.json" is not the same as "the script runs
and produces the expected output." `install_statusline.sh` therefore always
runs `health_check.sh` at the end and exits non-zero if any check fails.
Treat any "complete!" report from any agent that lacks evidence as suspect.

### Rule 3 — The statusline is a hot path: budget subprocesses, not just correctness

A statusline script looks like UI polish, but it executes on **every refresh in
every concurrent agent session**. Whatever it spawns gets multiplied by refresh
rate × number of live sessions, all day. Measured on a machine running many
concurrent sessions: a package-runner statusline (`bunx <pkg>@latest`-style,
which re-resolves the registry and re-writes a lockfile per refresh, then runs
`git status` + `git branch`) cost ~0.4s CPU per refresh; this script costs
~0.01s. Across many sessions that difference is a measurable share of
machine-wide process churn, heat, and battery — the statusline was one of the
top contributors found in a real battery-drain investigation (2026-07).

Concretely:
- **Never resolve packages at refresh time.** No `bunx`/`npx` `@latest` in
  `statusLine.command` — pin and install once, or use a local script.
- **Don't spawn `git` for the branch.** Read `.git/HEAD` as a file (see
  `git_branch_fast` in the script) — same answer, zero subprocesses.
- **Treat `git status` (dirty state) as a luxury.** It walks the worktree on
  every refresh; only the full layout runs it, and only when explicitly enabled.
- **Budget: a statusline refresh should cost single-digit milliseconds and
  a handful of forks at most** (one `jq` + one `awk` here).

For field-level traps (`used_percentage` null at session start, `total_input_tokens`
semantics across Claude Code versions, hardcoded `context_window_size`), see
[`references/context-window-schema.md`](references/context-window-schema.md).

## Customization

For colors, custom segments (hostname, time, etc.), and disabling cost tracking,
see [`references/customization.md`](references/customization.md).

## Dependencies

The script auto-detects available tools and degrades gracefully:

| Tool | Required for | Fallback |
|------|-------------|----------|
| `jq` | JSON parsing (preferred) | falls back to `python3` |
| `python3` | JSON parsing fallback | bare `cwd` only |
| `awk` | token K/M formatting | required by both layouts |
| `git` | dirty-state `*`/`+` markers (full layout only — minimal reads the branch from `.git/HEAD` without git) | silent skip if missing or not in repo |
| `ccusage` | cost (full layout) | silent skip if missing |

Install on macOS: `brew install jq`. On Debian/Ubuntu: `apt install jq`.

## Troubleshooting

For symptom-by-symptom diagnostics, see
[`references/troubleshooting-decision-tree.md`](references/troubleshooting-decision-tree.md).
It walks through:

1. Statusline blank or never updates (chmod cause)
2. ctx segment missing or wrong (field traps)
3. Want token counts not percentages (layout switch)
4. Colors render as raw escape codes (terminal compatibility)
5. Git segment missing (full layout)
6. Cost segment missing (ccusage / cache)
7. Edits have no effect (path mismatch)
8. Slow refresh (jq vs python3)

## Resources

| File | Purpose |
|------|---------|
| `scripts/generate_statusline.sh` | The statusline script. Single source of truth. Two layouts via `CLAUDE_STATUSLINE_LAYOUT`. |
| `scripts/install_statusline.sh` | Idempotent installer. Backs up, copies, chmods, wires `settings.json`, runs health check. |
| `scripts/health_check.sh` | Four-layer verification: file perms, settings.json wiring, mock stdin tests, real stdin replay. |
| `references/troubleshooting-decision-tree.md` | Symptom-driven diagnostic flowchart. Load when statusline misbehaves. |
| `references/customization.md` | Color changes, custom segments, threshold tuning, single-line full layout. Load when user wants to modify how the statusline looks. |
| `references/context-window-schema.md` | Claude Code statusline JSON schema. Documents every field plus `current_usage` vs `total_input_tokens` semantics across versions. |
| `references/color_codes.md` | ANSI color codes reference. Load for color customization. |
| `references/ccusage_integration.md` | ccusage integration deep-dive: caching, JSON shape, troubleshooting. Load for cost-related issues. |

© daymade · MIT · daymade/claude-code-skills

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set68

meeting-minutes-taker Converts raw meeting transcripts into structured, evidence-based minutes, resolves anonymous speakers, and merges parallel drafts without losing details. CX Codex +1 1,500installs fact-checker The skill pulls verifiable claims out of a document, checks them against official sources and proposes corrections. Useful when versions, numbers or model specs in your text have gone stale. CX Codex +1 1,500installs promptfoo-evaluation A skill that walks the agent through setting up Promptfoo evaluations: promptfooconfig.yaml, Python assertions, and LLM-as-judge rubrics. CX Codex +1 1,500installs skills-search Searches configured local repositories before CCPM, then manages skill packages when needed. Use it to discover, inspect, install, update or remove skills. CX Codex +1 1,400installs transcript-fixer Corrects ASR/STT errors in transcripts: homophones, garbled terms, wrong names, mixed Chinese and English. Useful for meeting notes, lectures and interviews. CX Codex +1 1,200installs pdf-creator Turn Markdown files into PDFs for print or phone reading, with selectable themes. Use it when a document needs to be delivered as a PDF rather than a Word file. CX Codex +1 1,000installs capture-screen A skill for programmatic screenshot capture on macOS: it finds window IDs, changes the view through AppleScript and grabs the frame with screencapture. CX Codex +1 1,000installs docs-cleaner A skill that keeps documentation honest after code changes and merges redundant files without losing what mattered. CX Codex +1 996installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor