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.
npx agentmods add skills/bouob/claude-statusline/customizenpx skills add bouob/claude-statusline --skill customizegit clone --depth 1 https://github.com/bouob/claude-statuslineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bouob/claude-statusline/customize)<a href="https://agentmods.dev/skills/bouob/claude-statusline/customize"><img src="https://agentmods.dev/badge/skills/bouob/claude-statusline/customize.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00063 | $0.01630 |
| Opus 5 | $0.00032 | $0.00815 |
| Sonnet 5 | $0.00013 | $0.00326 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
customize scanned grade A with 0 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 5d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
customize
Customize claude-statusline themes, styles, colors, and segments without manually editing JSON.
Dispatch on $ARGUMENTS
| Condition | Mode |
|---|---|
| No arguments | Wizard — interactive step-by-step setup |
| Contains "show", "current", "status", "list" | View — display current config |
| Other text | Quick edit — parse intent and update fields |
Config files
Priority order (first found wins on read; user-level is default write target):
./.claude-statusline.json— project-level~/.claude/claude-statusline.json— user-level
Valid values
Read valid themes, separators, bar styles, color keys, and segment names from the source:
- Themes:
${CLAUDE_SKILL_DIR}/../../src/themes/(one file per theme) - Defaults:
${CLAUDE_SKILL_DIR}/../../src/config/defaults.ts - Types:
${CLAUDE_SKILL_DIR}/../../src/config/types.ts
Color format: #RGB or #RRGGBB (hex). Validate with /^#([0-9A-Fa-f]{3}|[0-9A-Fa-f]{6})$/.
Segments (12)
model, context-bar, session, git, project, worktree, rate-limit, promotion, status, pr, agent, effort
pr, agent, and effort render only when their stdin field is present (recent Claude Code, approx v2.1.200+).
Each segment supports enabled: boolean. Some have additional sub-options:
| Segment | Sub-options |
|---|---|
context-bar |
width, showPercentage |
session |
showCost, showDuration, showLines |
rate-limit |
cacheSeconds, showFiveHour, showSevenDay, showResetTime, showBar, barWidth, barStyle, rainbow |
status |
cacheTtlSeconds |
effort |
showThinking |
Rainbow behavior
The progress bar automatically shifts to rainbow gradient. It also triggers when stdin reports exceeds_200k_tokens. Configurable via rainbow object:
| Field | Type | Default | Effect |
|---|---|---|---|
contextThreshold |
number |
90 |
Context % that triggers rainbow |
onAgent |
boolean |
false |
Rainbow during --agent sessions (opt-in) |
onWorktree |
boolean |
false |
Rainbow when in worktree (opt-in) |
alwaysOn |
boolean |
false |
Force rainbow regardless of context |
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.
- 5d ago First seen · 178 lines · 63 tokens per session scan A ffea6832efbd
customize is a skill published in the GitHub repository bouob/claude-statusline (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,630 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
usage-hud
Configure and customize the Usage HUD statusline display.
setup
Interactive setup for model-guard — asks three quick preference questions (band language, account display, auto-recovery), copies the statusline script, registers the statusLine in /.claude/settings.json (with a timestamped backup) and checks the keystroke channel the recovery hooks need. Safe to re-run anytime to…
remove
Cleanly uninstall the model-guard statusline — unregisters statusLine from /.claude/settings.json (restoring any previously saved statusline), and optionally deletes the installed script and config.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.