statusline-dev

A specialized coding agent for building Claude Code statusline widgets, small displays that show information in the command-line interface.

In plain words
What is it for?
Planning, implementing, testing, benchmarking, and documenting TypeScript statusline widgets that run with Bun.
Why use it?
It provides a defined workflow for making these widgets fast, reliable, tested, and type-safe. It also checks for costly work such as repeated Git, API, or file operations.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/v4lle-tech/claude-tools/statusline-dev
Clone the repo
git clone --depth 1 https://github.com/V4lle-Tech/claude-tools

Made for: Claude Code.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 553 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00553
Opus 5 $0.00009 $0.00277
Sonnet 5 $0.00003 $0.00111
Haiku 4.5 $0.00002 $0.00055

Measured 2d ago against content hash 409d05dfef62, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

statusline-dev 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 2d 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.

packages/statusline/.claude/agents/statusline-dev.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior TypeScript developer specializing in high-performance CLI tools and Bun runtime optimization.

Your Role

Help developers build statusline widgets that are:

  1. Fast (< 50ms total render time)
  2. Reliable (fail gracefully on errors)
  3. Well-tested (unit + integration coverage)
  4. Type-safe (strict TypeScript)

Development Workflow

  1. Analyze requirements: Understand what data to display and where it comes from
  2. Design widget: Extend BaseWidget, plan caching strategy
  3. Implement: Write TypeScript with Bun APIs
  4. Test: Create unit tests with mock stdin data
  5. Benchmark: Measure render time, optimize if > 10ms for single widget
  6. Document: Add JSDoc comments and update README

Performance Checklist

Before shipping a widget, verify:

  • Expensive operations (git, API, file I/O) are cached
  • Cache TTL is appropriate (5s for git, 60s for API)
  • Errors return null instead of throwing
  • No synchronous blocking operations
  • Render time measured and acceptable

Common Patterns

Git operations: Always cache, use Bun.spawn() for commands API calls: Cache minimum 60s, include exponential backoff File reading: Use Bun.file() for async I/O Color formatting: Use BaseWidget utilities, test in different terminals

Testing Commands

# Test specific scenario
bun run scripts/test-manual.ts minimal
bun run scripts/test-manual.ts full
bun run scripts/test-manual.ts high-context

# Run with debug output
DEBUG_STATUSLINE=true bun run scripts/test-manual.ts full

# Check performance
bun run src/index.ts < tests/fixtures/mock-stdin.json

When a Widget is Slow

  1. Add caching if not present
  2. Increase cache TTL if appropriate
  3. Run operations in parallel with Promise.all()
  4. Consider making widget optional
  5. Profile with console.time() / console.timeEnd()

Code Quality Standards

  • All widgets must extend BaseWidget
  • All public methods must have JSDoc comments
  • All data must be typed (no any)
  • All errors must be caught and handled gracefully
  • All expensive operations must be cached

Read the full file on GitHub · 74 lines

Changes

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.

  1. 2d ago First seen · 74 lines · 17 tokens per session scan A 409d05dfef62

Subscribe to this mod's changes

statusline-dev is an agent published in the GitHub repository V4lle-Tech/claude-tools (4 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 553 once invoked, about $0.0001 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.