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.
git clone --depth 1 https://github.com/Matt-Dionis/claude-code-configsWrote 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/commands/matt-dionis/claude-code-configs/ai-experimental-setup)<a href="https://agentmods.dev/commands/matt-dionis/claude-code-configs/ai-experimental-setup"><img src="https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/ai-experimental-setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/matt-dionis/claude-code-configs/ai-experimental-setup"><img src="https://agentmods.dev/badge/commands/matt-dionis/claude-code-configs/ai-experimental-setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00008 | $0.05325 |
| Opus 5.5 | $0.00003 | $0.02130 |
| Sonnet 5.5 | $0.00002 | $0.01065 |
| Haiku 4.5 | $0.00001 | $0.00532 |
Grade A, and why
ai-experimental-setup scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const response = await fetch(process.env.FEATURE_FLAG_SERVICE_URL, { How it starts
The opening of the file, as written. The whole thing — 793 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enable Experimental AI SDK Features
Configure and safely enable cutting-edge AI SDK experimental features: $ARGUMENTS
Current Experimental Status
Existing experimental features: !grep -r "experimental\|beta\|alpha" . --include="*.ts" --include="*.json" | head -5
Feature flags: !grep -r "ENABLE_\|FLAG_" .env* 2>/dev/null | head -3 || echo "No feature flags found"
Advanced configurations: !grep -r "streamingTimeouts\|thinkingMode\|toolCallStreaming" . --include="*.ts" | head -5
Experimental Feature Categories
Beta Features: Stable experimental features ready for production testing Experimental: Cutting-edge features in active development Research: Bleeding-edge research features for experimentation Custom: Custom experimental implementations and modifications
Your Task
- Analyze experimental feature landscape and identify safe options
- Implement feature flag system for controlled rollouts
- Configure experimental AI SDK options with proper safeguards
- Set up A/B testing framework for feature validation
- Add monitoring and telemetry for experimental features
- Create fallback mechanisms for experimental feature failures
- Implement gradual rollout strategy with user controls
- Add comprehensive testing for experimental features
Implementation Requirements
Feature Flag System
- Environment-based feature control
- User-level feature toggles
- Percentage-based rollouts
- Real-time feature flag updates
- Fallback mechanisms for failures
Safety Measures
- Automatic fallback to stable features
- Error isolation and reporting
- Performance impact monitoring
- User experience protection
- Data integrity guarantees
Experimental Configuration
- Advanced streaming options
- Cutting-edge model features
- Research-level AI capabilities
- Custom provider integrations
- Performance optimizations
Expected Deliverables
- Feature flag system with environment and user controls
- Experimental AI SDK configurations with safety controls
- A/B testing framework for feature validation
- Monitoring and telemetry for experimental features
- Fallback mechanisms for reliability
- Documentation for experimental feature usage
- Testing suite covering experimental scenarios
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.
- 1mo ago First seen · 793 lines · 8 tokens per session scan A 82e550a19cac
ai-experimental-setup is a command published in the GitHub repository Matt-Dionis/claude-code-configs (619 stars, last pushed 1y ago), licensed MIT. It adds 8 tokens to every session and 5,325 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
test-prompt
Test an AI prompt against multiple scenarios to verify consistent, quality output.
ai-feature-eval-harness
Design an eval plan for a product AI feature: success criteria, a held-out labeled dataset, per-criterion grading (code-based, then LLM-based), and a pass threshold. Use when a task ships or changes a feature with non-deterministic model output (classification, extraction, summarization, ranking, agent action) needing…
caracterizar-prompt
Characterization de prompts/tools LLM em produção — temperature=0 + seed fixo + sanitização específica. Trata prompts como código legacy. Modernização 2026 sem precedente em 2004.
promptfoo
Run promptfoo live agent tests (AnyRouter rubric).
prompt-eval-debug
Debug any prompt with a tiny eval suite (control, edge, boundary), failure diagnosis, and smallest next change, no blind rewrite.