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/warunacds/ccstatuswidgets/claude-mdgit clone --depth 1 https://github.com/warunacds/ccstatuswidgetsWrote 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/warunacds/ccstatuswidgets/claude-md)<a href="https://agentmods.dev/instructions/warunacds/ccstatuswidgets/claude-md"><img src="https://agentmods.dev/badge/instructions/warunacds/ccstatuswidgets/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 | $0.02359 | $0.02359 |
| Opus 5 | $0.01179 | $0.01179 |
| Sonnet 5 | $0.00472 | $0.00472 |
| Haiku 4.5 | $0.00236 | $0.00236 |
Grade B, and why
ccstatuswidgets CLAUDE.md scanned grade B with 1 finding 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 3d 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.
| effort | effort.go | file | Reads ~/.claude/settings*.json | How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ccstatuswidgets
What This Is
A Go binary (ccw) that provides a customizable, multi-line status line for Claude Code CLI. Reads JSON from stdin, runs widgets concurrently, renders colored ANSI output to stdout.
Repo: github.com/warunacds/ccstatuswidgets
Module: github.com/warunacds/ccstatuswidgets
Binary: ccw
Go version: 1.21+
Dependencies: stdlib only (no external deps)
License: MIT
Build & Test
go test ./... # all tests
go test ./... -race # with race detector
go vet ./... # lint
go build -o ccw ./cmd/ccw # build binary
Architecture
stdin JSON (from Claude Code)
│
▼
┌─────────────────┐
│ cmd/ccw/main.go │ ─── CLI routing (init, doctor, configure, pomo, etc.)
└────────┬────────┘
│ pipeline mode (no args)
▼
┌─────────────────┐ ┌──────────────────┐
│ config.Load() │ ──▸ │ widget.Registry │ ◂── widgets.RegisterAll() + plugin.DiscoverPlugins()
└────────┬────────┘ └────────┬─────────┘
│ │
▼ ▼
┌─────────────────────────────────────┐
│ engine.Run() │
│ Launches all widgets concurrently │
│ 500ms timeout per widget │
│ Cache fallback on timeout/error │
└────────────────┬────────────────────┘
│
▼
┌─────────────────────────────────────┐
│ renderer.Render() │
│ Per-widget styling (fg/bg/bold) │
│ Custom separators / Powerline │
│ ANSI color output │
└────────────────┬────────────────────┘
│
▼
stdout (colored text)
Package Map
| Package | Responsibility | Key Types/Functions |
|---|---|---|
cmd/ccw |
Entry point, CLI routing | main(), runPipeline() |
internal/protocol |
Data types | StatusLineInput, WidgetOutput, ModelInfo, ContextInfo, RateLimits, CostInfo |
internal/widget |
Widget interface + registry | Widget interface (Name(), Render()), Registry (Register, Get, Names) |
internal/widgets |
23 built-in widget implementations | One file per widget, RegisterAll() in register.go |
internal/engine |
Concurrent executor | Engine.Run() — goroutines per widget, timeout, cache fallback |
internal/renderer |
ANSI output | Render(), WidgetStyle, FgCode/BgCode, Powerline mode |
internal/cache |
File-based TTL cache | Cache.Get(), Cache.Set() — atomic writes in ~/.ccstatuswidgets/cache/ |
internal/config |
JSON config | Config struct, Load(), Save(), Default(), ConfigDir() |
internal/httpclient |
Shared HTTP client | Client.Get(), Client.GetWithHeaders() — 3s timeout |
internal/plugin |
External plugin runner | DiscoverPlugins(), ExternalWidget (implements Widget interface) |
internal/cli |
CLI commands | One file per command (init, doctor, configure, pomo, track, hn, plugin, list, add, remove, etc.) |
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.
- 3d ago First seen · 213 lines · 2,359 tokens per session scan B b3a681a3f8ed
ccstatuswidgets CLAUDE.md is an instructions file published in the GitHub repository warunacds/ccstatuswidgets (2 stars, last pushed 5mo ago), licensed MIT. It adds 2,359 tokens to every session, about $0.0118 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
boxento AGENTS.md
AGENTS.md instructions for sushaantu/boxento, covering ai agent instructions, boxento widget ux contract, source of truth in code, core principle and shell rules.
statuslin.es CLAUDE.md
Instructions for NathanAB/statuslin.es, covering statuslin.es, stack, architecture, the quality bar — non-negotiable and scope control.
xtool CLAUDE.md
Instructions for 2389-research/xtool, covering xtool plugin, skills included, using-xtool (main skill), key patterns and xtool is not xcodegen.
statuslin.es AGENTS.md
Instructions for NathanAB/statuslin.es, a project described as: Community gallery of Claude Code status lines.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.