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/agent-integration-testingnpx skills add av/harbor --skill agent-integration-testinggit 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 | $0.00020 | $0.00800 |
| Opus 5 | $0.00010 | $0.00400 |
| Sonnet 5 | $0.00004 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
agent-integration-testing 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Integration Testing
Overview
This skill guides the creation and autonomous execution of verifiable integration test specifications. It ensures that tests are actionable by agents, properly documented, and systematically executed by subagents to validate features or fix failures.
Core Process
-
Investigate Codebase Area
- By default, investigate the entire codebase to understand the context.
- If the user specifies a feature area, use
globandgrepto narrow the investigation.
-
Write Test Specification
- Create a test spec file at
./tests/<name>.md. - Use
<name> = "integration"unless the user specifies a particular feature area. - The document MUST include a Prerequisites section at the top detailing any setup needed before tests become runnable (e.g., environment variables, database seeding, background services).
- Create a test spec file at
-
Define Verifiable Tests
- Each test must be written in plain English.
- Include clear steps to reproduce.
- Include a set of expectations.
- CRITICAL: Every expectation must be strictly verifiable by an agent using available tools (e.g., shell commands, HTTP requests, reading file outputs). If a test cannot be verified by an agent, it is invalid and must be rewritten or removed.
-
Execute Tests via Subagents
- Spawn subagents (using the
Tasktool or@mentionsubagent system) to run each individual test. - The subagent must follow the prerequisites, execute the steps, and validate the outcomes against the expectations.
- Collect the results (Pass/Fail and logs) from the subagents.
- Spawn subagents (using the
-
Fix Failures (Optional)
- If the user explicitly specifies that failures should be fixed, spawn another subagent (e.g., the
SWEorBUILDERagent) to investigate and fix any noted failures.
- If the user explicitly specifies that failures should be fixed, spawn another subagent (e.g., the
Quick Reference
| Action | Pattern / Command |
|---|---|
| Test File Location | ./tests/<name>.md (default: integration.md) |
| Prerequisites | Must be documented at the top of the test file |
| Test Format | Plain English, Repro Steps, Verifiable Expectations |
| Execution | Spawn one subagent per test or test suite |
| Fixing | Spawn SWE/BUILDER subagent if requested by user |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 70 lines · 20 tokens per session scan A 449d97875c6f
agent-integration-testing is a skill published in the GitHub repository av/harbor (3,202 stars, last pushed 3d ago), licensed Apache-2.0. It adds 20 tokens to every session and 800 once invoked, about $0.0001 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-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.
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.
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.
service-manage
Manage services in Kurtosis enclaves. Add, inspect, stop, start, remove, update services. View logs, shell into containers, and execute commands. Use when you need to interact with running services.
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.