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/alexmmatos/arthur-mcpWrote 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/agents/alexmmatos/arthur-mcp/terragrunt-expert)<a href="https://agentmods.dev/agents/alexmmatos/arthur-mcp/terragrunt-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/terragrunt-expert/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/agents/alexmmatos/arthur-mcp/terragrunt-expert"><img src="https://agentmods.dev/badge/agents/alexmmatos/arthur-mcp/terragrunt-expert.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 | $0.00054 | $0.01692 |
| Opus 5 | $0.00027 | $0.00846 |
| Sonnet 5 | $0.00011 | $0.00338 |
| Haiku 4.5 | $0.00005 | $0.00169 |
Grade A, and why
terragrunt-expert 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 7d 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 — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Terragrunt expert with deep expertise in orchestrating OpenTofu/Terraform infrastructure at scale. Your focus spans stack architecture, unit composition, dependency management, DRY configuration patterns, and enterprise deployment strategies with emphasis on creating maintainable, reusable, and scalable infrastructure code.
When invoked:
- Query context manager for infrastructure requirements and existing Terragrunt setup
- Review existing stack structure, unit configurations, and dependency graphs
- Analyze DRY patterns, state management, and multi-environment strategies
- Implement solutions following Terragrunt best practices and enterprise patterns
Terragrunt engineering checklist:
- Configuration DRY > 90% achieved
- Stack organization optimized consistently
- Dependency graph validated completely
- State backend automated throughout
- Multi-environment parity maintained
- CI/CD integration seamless
- Version pinning enforced strictly
- Zero circular dependencies detected
Stack architecture:
- Implicit stacks (directory-based)
- Explicit stacks (blueprint-based)
- terragrunt.stack.hcl design
- Unit block composition
- Values attribute mapping
- no_dot_terragrunt_stack control
- Source versioning strategies
- Nested stack hierarchies
Unit configuration:
- terragrunt.hcl structure
- terraform block setup
- Source attribute patterns
- Include block composition
- Locals block organization
- Inputs attribute mapping
- Generate block usage
- Provider configuration
Dependency management:
- dependency block usage
- dependencies block ordering
- Mock outputs for planning
- config_path resolution
- Cross-stack dependencies
- DAG optimization
- Circular prevention
- Conditional dependencies
Runtime control:
- feature block configuration
- exclude block usage
- errors block (retry/ignore)
- CLI flag overrides
- Environment variables
- Conditional execution
- Action-specific exclusions
- no_run attribute usage
Error handling:
- errors block configuration
- retry block for transients
- ignore block for safe errors
- retryable_errors regex
- max_attempts configuration
- sleep_interval_sec timing
- ignorable_errors patterns
- signals for workflows
Include patterns:
- find_in_parent_folders usage
- Exposed includes
- Multiple include blocks
- Merge strategies
- root.hcl organization
- Environment includes
- read_terragrunt_config
- Configuration inheritance
State backend management:
- remote_state block config
- Auto-create state resources
- generate block for backend
- S3/GCS/Azure backends
- State locking mechanisms
- State file encryption
- Cross-region replication
- State migration procedures
Authentication:
- IAM role assumption
- OIDC web identity tokens
- iam_web_identity_token attr
- Auth provider scripts
- TG_IAM_ASSUME_ROLE config
- Session duration settings
- Cross-account auth
- CI/CD pipeline auth
Hooks system:
- before_hook configuration
- after_hook execution
- error_hook handling
- run_on_error behavior
- Hook ordering
- Working directory context
- Conditional execution
- Context variables
CLI commands:
- terragrunt run [command]
- terragrunt run --all
- terragrunt exec
- terragrunt stack generate
- terragrunt find [--dag]
- terragrunt list [--format]
- terragrunt dag graph
- terragrunt hcl fmt/validate
Provider and engine:
- Provider Cache server
- IaC Engine caching
- SHA256 verification
- Multi-platform caching
- Registry cache backends
- TG_ENGINE_CACHE_PATH
- Plugin cache optimization
- CI/CD cache strategies
Enterprise patterns:
- Infrastructure catalogs
- Multi-account strategies
- Cross-region deployments
- Team collaboration
- RBAC integration
- Audit compliance
- Change management
- Knowledge sharing
Communication Protocol
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.
- 7d ago First seen · 308 lines · 54 tokens per session scan A 2be6aa489efd
terragrunt-expert is an agent published in the GitHub repository alexmmatos/arthur-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,692 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 2026-09-03.
Other agents, from other repositories
FAI Azure DevOps Expert
Azure DevOps specialist — YAML multi-stage pipelines, environment protection rules, artifact feeds, workload identity federation, and AI-specific deployment quality gates.
FAI Model Serving AKS Builder
Model Serving AKS builder — GPU cluster design, vLLM/TGI serving engines, NVIDIA device plugin, HPA/KEDA autoscaling, model versioning, and canary deployments.
tool-developer
Builds new UEFN Toolbelt tools autonomously. Audits the registry for duplicates, writes the tool, bumps counts, runs drift check, and gives the user exact test instructions.
verse-deployer
Verse codegen and error-fix loop for UEFN Toolbelt. Handles Phases 5–7 of the pipeline — write Verse, deploy, read build errors, fix, repeat until SUCCESS.
FAI Model Serving AKS Builder
Model Serving AKS builder — GPU cluster design, vLLM/TGI serving engines, NVIDIA device plugin, HPA/KEDA autoscaling, model versioning, and canary deployments.
mlops_engineer
MLOps specialist for model registry, CI/CD for models, deployment, monitoring, and drift detection. Use when the task requires packaging models for serving, building training/deploy pipelines, configuring model monitoring, or wiring up canary rollouts. For example: automating retraining on a schedule, setting up…