A set of instructions for pyATS, Cisco's Python framework for testing and automating network devices. It explains testbeds, secure credentials, device commands, configuration, parsing, parallel actions, and several test-writing approaches.

Use it to create or maintain network testbeds and tests, run commands or configuration changes, collect device state, test many devices in parallel, use simulated devices, or work with REST connections and containers.

It helps an agent choose the right pyATS operation and structure network tests without confusing device discovery, commands, configuration, and verification.

pyats — Skill for Claude Code and Codex by automateyournetwork

Install

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.

Any agent

npx skills add automateyournetwork/pyATS_skills --skill pyats

Clone the repo

git clone --depth 1 https://github.com/automateyournetwork/pyATS_skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/automateyournetwork/pyats_skills/pyats/github.svg)](https://agentmods.dev/skills/automateyournetwork/pyats_skills/pyats)

Your own site

<a href="https://agentmods.dev/skills/automateyournetwork/pyats_skills/pyats"><img src="https://agentmods.dev/badge/skills/automateyournetwork/pyats_skills/pyats/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/automateyournetwork/pyats_skills/pyats"><img src="https://agentmods.dev/badge/skills/automateyournetwork/pyats_skills/pyats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,376 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00102	$0.01376
Opus 5	$0.00051	$0.00688
Sonnet 5	$0.00020	$0.00275
Haiku 4.5	$0.00010	$0.00138

Measured 10d ago against content hash 2c264f64349f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

pyats scanned grade C 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Clean (`references/clean.md`) is destructive by design** — device reset/reprovisioning (erase, reload, reinstall image). Treat it with the same caution as `rm -rf`: confirm scope before running.

skills/pyats/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pyATS

pyATS (with Genie and Unicon) is Cisco's Python network test-automation framework: everything starts from a testbed (a device/connection model), and builds up through primitives (learn/parse/execute/configure) into test-authoring layers (AEtest, Blitz, Robot Framework, Genie triggers/verifications) and operational tooling (Clean, mock devices, REST, containers, XPRESSO, Webex, health checks).

This file carries the concepts and decision logic. Detailed, topic-specific material lives in references/ and should be loaded only when that topic is actually relevant to the task at hand.

Core concepts

Everything starts from a testbed. It's not just a static YAML file — it's a live device/connection object graph that can be built dynamically at runtime from a northbound API/inventory system just as validly as from YAML on disk. See references/testbeds.md.
Credentials are never hardcoded. pyATS has dedicated markup (%ENV{}, %ASK{}, %ENC{}, %CALLABLE{}) and a SecretString type for this. See references/secret-strings.md.
The four core primitives are distinct tools:
- .learn() — vendor-neutral, multi-command Ops object for a feature (OSPF, BGP, interfaces...). See references/learn.md.
- .parse() — structured output of exactly one named show command. See references/parse.md.
- .execute() / .configure() — raw CLI / pushing config, with Dialog/Statement prompt handling and a safe check→apply→verify discipline. See references/execute-configure.md.
- pcall — running any of the above across many devices in parallel instead of a sequential loop. See references/pcall.md.
Four ways to author a test, in order of "how much code":
- AEtest (Python, references/aetest.md) — for genuinely custom/branching logic.
- Blitz (declarative YAML, references/blitz.md) — for straightforward parse/execute/configure/verify sequences.
- Robot Framework (references/robot-framework.md) — only when a team is already standardized on Robot.
- Genie triggers/verifications (references/genie-triggers-validations.md) — reusable, config-driven checks meant to run unchanged across many environments.
Clean (references/clean.md) is destructive by design — device reset/reprovisioning (erase, reload, reinstall image). Treat it with the same caution as rm -rf: confirm scope before running.
Mock/recorded devices (references/mock-devices.md) simulate a device for CI/demos — distinct from snapshot/diff, which compares real operational state over time.
REST connectivity (references/rest-connector.md) is a separate, complementary transport to CLI for API-based devices/controllers.
Operational layer: references/containers.md (running pyATS in Docker), references/xpresso.md (the web dashboard for managing suites/testbeds/results at scale), references/webex.md (posting results to chat), references/health-check.md (CPU/memory/logging/crash monitoring around test runs).

Read the full file on GitHub · 62 lines

Files

What ships with it

21 files 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.

Changes

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.

10d ago First seen · 62 lines · 102 tokens per session scan C 2c264f64349f

Subscribe to this mod's changes

pyats is a skill published in the GitHub repository automateyournetwork/pyATS_skills (11 stars, last pushed 20d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,376 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

pyats