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 yaalalabs/agent-kernel --skill ak-testgit clone --depth 1 https://github.com/yaalalabs/agent-kernelWrote 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/yaalalabs/agent-kernel/ak-test)<a href="https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-test"><img src="https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-test/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/yaalalabs/agent-kernel/ak-test"><img src="https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-test.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 | $0.00047 | $0.03830 |
| Opus 5.5 | $0.00019 | $0.01532 |
| Sonnet 5.5 | $0.00009 | $0.00766 |
| Haiku 4.5 | $0.00005 | $0.00383 |
Grade A, and why
ak-test scanned grade A with 2 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 8d 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.
5. Test health endpoint: `curl http://localhost:8000/health` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
# proc = subprocess.Popen(["python3", "app.py"], stdout=sys.stdout, stderr=sys.stderr) How it starts
The opening of the file, as written. The whole thing — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing & Debugging
Use this skill to set up testing for your Agent Kernel project or debug issues.
Instructions for the Agent
Setting Up Tests
1. Add Test Dependencies
Update pyproject.toml:
[dependency-groups]
dev = [
"agentkernel[test]>=0.9.5",
"black>=23.0.0",
"isort>=5.0.0",
"mypy>=1.0.0",
]
Run uv sync to install test dependencies.
2. Choose a Test Mode
Create test-config.yaml in the directory you run tests from — it is a separate, un-nested file
(no top-level test: key), loaded only when the test harness runs. A test: section left over in
config.yaml is ignored:
mode: score # Options: score | llm | fallback (default: fallback)
| Mode | How it Works | Best For |
|---|---|---|
| score | Deterministic string-match scoring (built-in deepeval: Scorer.quasi_exact_match_score; built-in opik: graded LevenshteinRatio; built-in jev has no score mode) |
Deterministic responses, exact answers |
| llm | LLM evaluates if response is semantically correct (deepeval and opik: GEval; jev: a hosted yes/no Noul question) |
Open-ended responses, creative agents |
| fallback | Tries score first, falls back to llm if score fails | General-purpose testing |
For llm mode, configure the llm model:
mode: llm
llm:
model: gpt-4o-mini
provider: openai
Evaluator backend: evaluator selects the scoring backend used by both score and llm
modes — deepeval (the default, pip install "agentkernel[test]"), opik (pip install "agentkernel[opik]", Opik by Comet, runs entirely locally) and jev
(pip install "agentkernel[jev]", hosted TypeSafe JEV judge: mode: llm only, needs
TYPESAFE_API_KEY, sends the comparison text to api.typesafe.ai) are the three built-ins. Set it to a dotted path (e.g. my_evaluator.MyEvaluator) to bring your own
AKEvaluator subclass instead:
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.
- 8d ago Changed 79c7ff05b081
- 9d ago Changed 7292d8d16fd5
- 16d ago Changed · +1 lines b6a3f20f3278
- 22d ago Changed c558397585ca
- 25d ago Changed 44a61d21e43b
- 1mo ago Changed 1372eac50abf
- 1mo ago Changed · +75 lines 270a80bdad52
- 1mo ago Changed · +19 lines f10eb2f63b55
- 1mo ago First seen · 341 lines · 47 tokens per session scan A 096268953b26
ak-test is a skill published in the GitHub repository yaalalabs/agent-kernel (192 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 3,830 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tdd
Test-Driven Development workflow for ALL Prowler components (UI, SDK, API). Trigger: ALWAYS when implementing features, fixing bugs, or refactoring - regardless of component. This is a MANDATORY workflow, not optional.
cloudflare
Cloudflare integration for DNS, CDN, WAF, edge diagnostics, and remediation with zone management, analytics, security events, and cache control.
thousandeyes
ThousandEyes network intelligence integration for monitoring tests, alerts, agents, Internet Insights outages, dashboards, and BGP routes during RCA investigations.
cloudbees
CloudBees CI integration for investigating builds, deployments, pipeline stages, and test results during RCA.
elastic
Elastic Cloud (Elasticsearch + Kibana) integration for discovering indices, searching logs with Lucene or ES|QL, and reading Kibana alerts during RCA investigations.
datadog-ninja
Master orchestrator for 57 official Datadog agent skills from DataDog/pup and datadog-labs/agent-skills. Use when working with ANY Datadog observability task: APM and distributed tracing, log search and pipelines, monitors and alerting, live production debugging, audit trail investigations, browser SDK…