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 skills/av/harbor/new-servicenpx skills add av/harbor --skill new-servicegit clone --depth 1 https://github.com/av/harborWhat 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 | $0.00139 | $0.03600 |
| Opus 5 | $0.00069 | $0.01800 |
| Sonnet 5 | $0.00028 | $0.00720 |
| Haiku 4.5 | $0.00014 | $0.00360 |
Grade A, and why
new-service 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 yesterday.
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.
(`curl`, `jq`, `sqlite`, `ssh-keygen`, etc.), **do not** install them with `apk add` in How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a New Service to Harbor
Subagent instruction: Before doing any work, read this skill file in full using the
read_filetool at path/home/everlier/code/harbor/.agents/skills/new-service/SKILL.md. Do not proceed until the file has been read.
Harbor is a modular Docker Compose project. Each service is a self-contained unit:
a compose file, a service directory, environment variables, app metadata, and documentation.
The detailed technical reference lives in .github/copilot-new-service.md — consult it
for edge cases or patterns not covered here.
Workflow Overview
Gather Info → Scaffold → Compose Config → Env Vars → Metadata → Documentation → Integrations → Test
Every step has validation criteria. Do not advance until the current step passes.
Step 0: Gather Information
Before writing any files, understand what you're building.
Required inputs:
- Service name or GitHub repo URL (from user)
- Docker deployment method: pre-built image, Dockerfile, or docker-compose in repo
- Service category: backend (inference), frontend (web UI), or satellite (tool/utility)
- Ports the service exposes internally
- Persistent data directories (volumes)
- Environment variables the service accepts
Research the repo. Look for:
docker-compose.yml,Dockerfile, ordocker/directory- README sections on Docker deployment, environment variables, configuration
- The service's default ports and data paths
If the repo has its own docker-compose, study the service definitions — you'll adapt them to Harbor's conventions, not copy them verbatim.
If ambiguous, ask the user. Don't guess the category or deployment method.
Step 1: Select a Handle
The handle is the service's identifier everywhere in Harbor.
Rules:
- Lowercase letters, numbers, hyphens only
- Short, memorable, representative
- Must be unique
Validate:
ls services/compose.${handle}.yml 2>/dev/null && echo "TAKEN" || echo "OK"
grep -q "\"${handle}\"\\|'${handle}'\\|${handle}:" app/src/serviceMetadata.ts && echo "TAKEN" || echo "OK"
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.
- yesterday First seen · 405 lines · 139 tokens per session scan A 3c2a3dece9d1
new-service is a skill published in the GitHub repository av/harbor (3,198 stars, last pushed 2d ago), licensed Apache-2.0. It adds 139 tokens to every session and 3,600 once invoked, about $0.0007 per session on Opus 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 2026-08-30.
Other skills, from other repositories
docker-local-build
Build and test Kurtosis from source on local Docker. Compiles all components (engine, core, files-artifacts-expander), builds Docker images, installs the CLI, and restarts the engine. Use when developing Kurtosis and testing changes locally with Docker.
files-inspect
Inspect, download, upload, and debug Kurtosis file artifacts. View artifacts in an enclave, download them locally for inspection, upload local files, and troubleshoot file mounting issues. Use when services can't find expected files or configs are wrong.
k8s-dev-deploy
Build, push, and deploy Kurtosis dev images to a Kubernetes cluster without creating a release. Rebuilds engine, core, and files-artifacts-expander as multi-arch Docker images with a unique tag, pushes to the logged-in user's Docker Hub, and restarts the engine. Use when testing local code changes on a k8s cluster.
starlark-dev
Develop and debug Kurtosis Starlark packages. Create packages from scratch, understand the plan-based execution model, use print() debugging, handle future references, and test packages locally. Use when writing or troubleshooting .star files.
docker-debug
Debug Kurtosis running on local Docker. Inspect engine, API container, and service logs. Diagnose container crashes, port conflicts, and networking issues. Use when kurtosis commands fail or services aren't reachable on Docker.
enclave-inspect
Inspect and manage Kurtosis enclaves. List enclaves, view services and ports, examine file artifacts, dump enclave state for debugging, and clean up. Use when you need to understand what's running inside an enclave or export its state.