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 skills add leeguooooo/claude-code-usage-bar --skill claude-statusbargit clone --depth 1 https://github.com/leeguooooo/claude-code-usage-barWrote 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/leeguooooo/claude-code-usage-bar/claude-statusbar)<a href="https://agentmods.dev/skills/leeguooooo/claude-code-usage-bar/claude-statusbar"><img src="https://agentmods.dev/badge/skills/leeguooooo/claude-code-usage-bar/claude-statusbar/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/leeguooooo/claude-code-usage-bar/claude-statusbar"><img src="https://agentmods.dev/badge/skills/leeguooooo/claude-code-usage-bar/claude-statusbar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 148 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Anti-Refusal · line 167 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 5.1 | $0.00275 | $0.02853 |
| Opus 5.5 | $0.00110 | $0.01141 |
| Sonnet 5.5 | $0.00055 | $0.00571 |
| Haiku 4.5 | $0.00028 | $0.00285 |
Grade C, and why
claude-statusbar 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 today.
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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Don't lecture about ANSI codes or terminal compatibility unless asked. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Claude Code's `~/.claude/settings.json` has the `statusLine` block How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-statusbar control skill
Use this skill any time the user wants to inspect, change, customize, or
diagnose the cs status bar. Replaces the older individual slash commands
(/statusbar, /statusbar-style, /statusbar-preview,
/statusbar-doctor, /statusbar-reset) — they still work but this skill
covers all of them with conversational intent.
Decision tree
Match the user's intent to the right cs command. Run it via Bash, then
give a short confirmation (one line, no lecture).
| User intent | Command |
|---|---|
| Inspect current config | cs config show |
| Pick a look interactively (user is in their own terminal) | tell them to run cs theme — ↑/↓ with live previews, Enter applies; from Claude Code use the config commands below instead |
Hide the ✦ New looks available line without picking |
cs config set looks_seen 1 (it goes away for good once cs theme has been opened) |
| List styles | cs styles |
| Aurora with ■ block bars (default look) | cs config set style aurora + cs config set bar_glyph block |
| Aurora with a thin ━ line ("细一点") | cs config set style aurora + cs config set bar_glyph thin |
| Original battery-bar look | cs config set style classic |
| Change density | cs config set density <compact|regular|cozy> |
| Show the three looks side by side | cs preview |
| Diagnose problem | cs doctor |
| Return one key to its default | cs config unset <key> (the config stores only what you changed) |
| Wipe config | cs config reset |
| Install / first-time setup | cs --setup |
| Upgrade / update to latest version | cs upgrade — NEVER guess uv tool install / pip install -U / pipx upgrade: it detects the install channel that is actually running cs and picks the right one (many users don't have uv at all) |
| Turn auto-upgrade off | cs config set auto_upgrade false (default true — a detached once-a-day check upgrades every install channel, binaries included; CLAUDE_STATUSBAR_NO_UPDATE=1 also wins) |
| Enable fast mode (daemon) | cs --setup --fast |
| Disable fast mode | cs daemon stop then re-run cs --setup |
| Toggle session cost display | cs config set show_cost true|false |
| Toggle prompt-cache countdown | cs config set show_cache_age true|false |
| Toggle project + branch 2nd line | cs config set show_project_branch true|false (default true) |
Toggle the ocs line (ocs boss · claude-7d5a5d07 · ✉3 · lan win: address, unread DMs, LAN bridge; own line; auto-hidden without ocs ≥ 0.5.0, ✉ needs an ocs whose inbox accepts --session) |
cs config set show_ocs true|false (default true) |
Toggle todo progress (▸ task 3/7, 3rd line) |
cs config set show_todos true|false (default true) |
Toggle active-tool indicator ◐ (3rd line) |
cs config set show_tools true|false |
Toggle completed-tool rollup ✓ name×N (3rd line) |
cs config set show_tool_rollup true|false (default off — volume tally) |
| Toggle running-subagent bottom line(s) | cs config set show_agents true|false (default off — Claude Code shows background agents natively) |
Toggle session duration ⏱ (on identity line) |
cs config set show_duration true|false |
Toggle lines added/removed +/- (on identity line) |
cs config set show_lines true|false |
Toggle git ahead/behind ↑↓ (on identity line) |
cs config set show_ahead_behind true|false |
Toggle the bar_shimmer twinkling starfield (experimental, classic only) |
cs config set bar_shimmer true|false (default off) |
| Toggle the rate-limit forecast (→NN% projected use / ⚠eta warning) | cs config set show_forecast true|false (default on) |
Toggle the faint version + update hint at the identity-line end (· vX.Y.Z ↑new) |
cs config set show_version true|false (default on) |
| Toggle the ⚙ session-mode line (effort/thinking/fast/output-style) | cs config set show_mode true|false (default off) |
| Toggle the per-effort colour gradient on the mode line | cs config set mode_gradient true|false (default on) |
| Hide weekly bar | cs config set show_weekly false |
| Set warning threshold | cs config set warning_threshold <0-100> |
| Set critical threshold | cs config set critical_threshold <0-100> |
| Force / disable no-quota (API) mode | cs config set api_mode <auto|on|off> |
| Show working directory | cs config set show_cwd true|false + cs config set cwd_style <basename|full> |
| Relay balance fuel gauge | cs config set show_balance true|false + cs config set balance_bar true|false (no-quota mode only; auto-hidden when the relay has no balance API) |
| Exit-IP purity segment (also checks IPv4 and IPv6 exits separately against our own host — warns on an IPv4/IPv6 split, WARP, VPN/proxy, or an unsupported region; never contacts Anthropic, and a per-domain proxy rule can still route claude.ai differently) | cs config set show_ip_risk true|false |
| Local custom-endpoint notice (no watermark or account prediction) | cs config set show_fp_risk true|false |
Window-end projection →NN% |
cs config set show_projection true|false |
Worktree count glyph (worktree (🌳3)) |
cs config set worktree_glyph ⑂ (default 🌳; any 1-2 cell symbol) |
| Worktree marker color | cs config set color_worktree "#bd93f9" (empty string restores the theme's hue) |
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.
- today Changed · -11 lines · +20 tokens per session d66994ae46cf
- 13d ago Changed 39075fa9b084
- 15d ago Changed · -16 lines · -26 tokens per session 0152e3d24046
- 23d ago Changed d8a894fb5906
- 1mo ago Changed · +1 lines ce4e0c4d7d81
- 1mo ago First seen · 180 lines · 281 tokens per session scan C 2c27ef8e13b9
claude-statusbar is a skill published in the GitHub repository leeguooooo/claude-code-usage-bar (380 stars, last pushed today), licensed MIT. It adds 275 tokens to every session and 2,853 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it C with 2 findings (strips warnings and disclaimers, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
council
Develop or review a plan, draft, workflow, decision, or argument using independent council members and a fresh synthesis. Use for an explicit council request, including dictated counsel. Discussing councils alone is not an invocation.
kit-setup
Check optional outside-agent connections and help complete their setup. Use when the user asks to connect agents, test Ask Agents, or troubleshoot the starter kit.
ask-agents
Send a specific question or task to the external agent or agents the user names and relay their responses. Use for an outside opinion or explicit request to ask Claude, Codex, or Gemini.