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 skills add kurtosis-tech/kurtosis --skill enclave-inspectgit clone --depth 1 https://github.com/kurtosis-tech/kurtosisWrote 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/skills/kurtosis-tech/kurtosis/enclave-inspect)<a href="https://agentmods.dev/skills/kurtosis-tech/kurtosis/enclave-inspect"><img src="https://agentmods.dev/badge/skills/kurtosis-tech/kurtosis/enclave-inspect/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/skills/kurtosis-tech/kurtosis/enclave-inspect"><img src="https://agentmods.dev/badge/skills/kurtosis-tech/kurtosis/enclave-inspect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.00859 |
| Opus 5 | $0.00026 | $0.00430 |
| Sonnet 5 | $0.00010 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
enclave-inspect 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 11d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enclave Inspect
Inspect and manage Kurtosis enclaves and their contents.
List enclaves
kurtosis enclave ls
Output shows enclave name, UUID, status (RUNNING/STOPPED), and creation time.
Inspect an enclave
kurtosis enclave inspect <enclave-name>
This shows:
- File Artifacts — uploaded files and rendered templates
- User Services — running containers with their ports and status
Services
View service details
# Full enclave inspection (shows all services with ports)
kurtosis enclave inspect <enclave-name>
# View logs for a service
kurtosis service logs <enclave-name> <service-name>
# Follow logs in real time
kurtosis service logs <enclave-name> <service-name> -f
# Shell into a service
kurtosis service shell <enclave-name> <service-name>
# Run a command in a service
kurtosis service exec <enclave-name> <service-name> -- <command>
Access service ports
The inspect output shows port mappings like:
http: 8545/tcp -> http://127.0.0.1:61817
This means port 8545 inside the container is mapped to localhost:61817. On Kubernetes with gateway running, these are forwarded through the gateway.
File artifacts
File artifacts are named blobs of files stored in the enclave.
# List artifacts (shown in enclave inspect)
kurtosis enclave inspect <enclave-name>
# Download an artifact to local disk
kurtosis files download <enclave-name> <artifact-name> /tmp/output-dir
# Upload a local file as an artifact
kurtosis files upload <enclave-name> /path/to/local/file
Dump enclave state
Export the full enclave state for offline debugging:
kurtosis enclave dump <enclave-name> /tmp/enclave-dump
# Verify the dump completed successfully
ls -la /tmp/enclave-dump/
This exports:
- Service logs
- Service configurations
- File artifacts
- Enclave metadata
Useful for sharing with others to debug issues.
Troubleshooting
| Symptom | Cause | Fix |
|---|---|---|
| Enclave not found | Typo or enclave was removed | Run kurtosis enclave ls to see available enclaves |
| Dump directory empty | Enclave has no services | Check kurtosis enclave inspect — enclave may be idle |
| Inspect shows STOPPED services | Services crashed or were stopped | Check logs with kurtosis service logs before restarting |
| K8s namespace missing | Enclave was cleaned up | Re-run the package to recreate the enclave |
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.
- 11d ago First seen · 139 lines · 52 tokens per session scan A bc4e4d01f857
enclave-inspect is a skill published in the GitHub repository kurtosis-tech/kurtosis (551 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 859 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 skills, from other repositories
docker-docs
Comprehensive Docker 28.x reference covering all features: installation, Dockerfile instructions, multi-stage builds, Docker Compose, networking, volumes, CLI commands, image management, registries, security best practices, CI/CD integration, debugging, and Kubernetes migration. Use whenever the user mentions Docker…
docker-management
Docker container lifecycle management, Dockerfile authoring, and debugging.
env-doctor
A diagnostic tool for checking a development environment, including runtimes, ports, and service health.
Pair Programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.