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/serpro69/claude-toolbox/eval-gradergit clone --depth 1 https://github.com/serpro69/claude-toolboxWhat 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 | $0.00052 | $0.01118 |
| Opus 5 | $0.00026 | $0.00559 |
| Sonnet 5 | $0.00010 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
eval-grader 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 80 lines · 52 tokens per session scan A 0bd98aa2a2b4
eval-grader is an agent published in the GitHub repository serpro69/claude-toolbox (148 stars, last pushed 2d ago), with no licence file. It adds 52 tokens to every session and 1,118 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
device-verification
Read this before running agent-device by hand against a simulator, emulator, or physical device.
mobile
Use for mobile app development, React Native, Flutter, iOS, Android, and cross-platform mobile tasks.
flutter-reviewer
Flutter 3.44 / Dart 3.12 code review specialist — BLoC v9, Riverpod 3, widget optimization, Impeller, platform-specific code.
reactnative-reviewer
React Native 0.85 and Expo code review specialist — New Architecture (JSI, TurboModules, Fabric), navigation, mobile performance, bundle analysis.
flutter-developer
Flutter/Dart cross-platform development, Riverpod state management, and platform channels specialist. Use when building Flutter apps, implementing state management, or working with native platform features. Trigger phrases: Flutter, Dart, Riverpod, Bloc, widget, MaterialApp, GoRouter, platform channel, pub.dev, build…
edge-ai-engineer
Edge AI deployment specialist for on-device inference using Google AI Edge Gallery, TFLite, ONNX Runtime, and MediaPipe with model quantization and hardware delegate optimization.