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 agents/v4lle-tech/claude-tools/statusline-devgit clone --depth 1 https://github.com/V4lle-Tech/claude-toolsWhat 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 | $0.00017 | $0.00553 |
| Opus 5 | $0.00009 | $0.00277 |
| Sonnet 5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00002 | $0.00055 |
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.
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:
- Fast (< 50ms total render time)
- Reliable (fail gracefully on errors)
- Well-tested (unit + integration coverage)
- Type-safe (strict TypeScript)
Development Workflow
- Analyze requirements: Understand what data to display and where it comes from
- Design widget: Extend BaseWidget, plan caching strategy
- Implement: Write TypeScript with Bun APIs
- Test: Create unit tests with mock stdin data
- Benchmark: Measure render time, optimize if > 10ms for single widget
- 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
nullinstead 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
- Add caching if not present
- Increase cache TTL if appropriate
- Run operations in parallel with
Promise.all() - Consider making widget optional
- 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
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.
- 2d ago First seen · 74 lines · 17 tokens per session scan A 409d05dfef62
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.