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 instructions/briansmith80/claude-code-status-bar/claude-mdgit clone --depth 1 https://github.com/briansmith80/claude-code-status-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/instructions/briansmith80/claude-code-status-bar/claude-md)<a href="https://agentmods.dev/instructions/briansmith80/claude-code-status-bar/claude-md"><img src="https://agentmods.dev/badge/instructions/briansmith80/claude-code-status-bar/claude-md.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 | $0.12459 | $0.12459 |
| Opus 5 | $0.06229 | $0.06229 |
| Sonnet 5 | $0.02492 | $0.02492 |
| Haiku 4.5 | $0.01246 | $0.01246 |
Grade B, and why
claude-code-status-bar CLAUDE.md scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Web configurator (`docs/index.html`, the `#configure` section)** — the landing page's "Build exactly the bar you want" section is an interactive, in-browser configurator. Pick theme/layout/segments, watch a live true Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Token security** — OAuth tokens are passed to curl via `--config -` (stdin), not command-line args, so they're hidden from `ps`. wget uses `--max-redirect=0` to prevent token leakage on redirects. Since v2.20.0 the w How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Status Bar — Project Guide
What this is
A configurable status bar for Claude Code. Pure bash core with optional Node.js helper for live activity. Cross-platform (macOS, Linux, Windows/MSYS2).
Architecture
VERSION # Single source of truth for version (bump ONLY this file for releases)
statusline-command.sh # The runtime script — installed to ~/.claude/
statusline-helper.js # Optional Node.js transcript parser — installed to ~/.claude/
statusline-subagent.js # Optional Node.js subagent panel renderer — installed to ~/.claude/
install.sh # Installer/updater — downloads script + helpers + VERSION from GitHub
install.ps1 # Windows PowerShell installer/updater — native JSON settings merge
.claude-plugin/plugin.json # Plugin manifest for marketplace distribution
.claude-plugin/marketplace.json # Marketplace catalog (required by /plugin marketplace add)
commands/setup.md # Slash command: /claude-code-status-bar:setup
commands/configure.md # Slash command: /claude-code-status-bar:configure
docs/assets/ # README images + their generators (hero, animated hero-demo.svg/.gif, banner pair, social card)
docs/assets/themes/ # per-theme --demo preview SVGs + generate-theme-demos.sh (captures real --demo output) + ansi-to-svg.js
README.md # User-facing docs
Installed files (at ~/.claude/)
| File | Purpose | Overwritten on update? |
|---|---|---|
statusline-command.sh |
The script Claude Code runs | Yes |
statusline-helper.js |
Node.js transcript parser (optional) | Yes |
statusline-subagent.js |
Node.js subagent panel renderer (optional) | Yes |
.statusline-version |
Local copy of VERSION | Yes |
statusline.conf |
User config overrides | Never (created from the template on first install only) |
statusline.conf.example |
Commented reference template (all options, all commented) | Yes |
.statusline-update-cache |
Update check cache (timestamp + version) | Cleared on update |
.statusline-usage-cache |
Usage API response cache (JSON) | Auto-refreshes every 10 min |
.statusline-activity-cache |
Transcript activity cache (JSON) | Auto-refreshes every call |
.statusline-claude-status-cache |
Claude API status cache (<epoch> <indicator>) |
Auto-refreshes every claude_status_cache_seconds (opt-in) |
.statusline-transcript-cache/ |
Parsed transcript cache (by SHA256) | Auto-invalidates on change |
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 · 189 lines · 12,459 tokens per session scan B 04f49de9efe1
claude-code-status-bar CLAUDE.md is an instructions file published in the GitHub repository briansmith80/claude-code-status-bar (17 stars, last pushed 1mo ago), licensed MIT. It adds 12,459 tokens to every session, about $0.0623 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
mirage CLAUDE.md
Claude Code instructions for strukto-ai/mirage, covering claude.md, repo layout, typescript packages, python/typescript parity and module layout.
ralph CLAUDE.md
Claude Code instructions for SantanderAI/ralph, covering ralph — instrucciones del proyecto and paridad bash ↔ powershell (importante).
claude-code-statusline CLAUDE.md
Instructions for glauberlima/claude-code-statusline, covering claude.md, project overview, development commands, testing and run all tests (unit + integration).
claude-wrapper CLAUDE.md
Instructions for smartwatermelon/claude-wrapper, covering claude.md, what this is, commands, run tests and lint.
auto-uv-env AGENTS.md
Instructions for ashwch/auto-uv-env, covering agents.md - the auto-uv-env story, what this repo is, architecture diagrams, runtime activation flow and repository lifecycle.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).