Agent skill

Pyats Config Mgmt

by automateyournetwork in automateyournetwork/netclaw

Direct, pyATS-based network change management - pre-change baselines, configuration deployment, post-change verification, rollback procedures, and compliance validation.

Apache-2.0Auto-check passedDevOps & Cloud

Install Pyats Config Mgmt

skills CLI
$ npx skills add automateyournetwork/netclaw --skill pyats-config-mgmt -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install automateyournetwork/netclaw pyats-config-mgmt --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workspace/skills/pyats-config-mgmt .claude/skills/pyats-config-mgmt && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pyats-config-mgmt
GitHub stars
676
Token cost
~3k tokens
SKILL.md length
694 words
Files
1
Skills in repo
120
Repo updated
First seen
Licence
Apache-2.0

At a glance

Direct, pyATS-based network change management - pre-change baselines, configuration deployment, post-change verification, rollback procedures, and compliance validation.

  • Works in 5 steps: Pre-Change Baseline → Plan the Change → Apply Configuration → …
  • Pushing config to a device
  • SKILL.md covers Golden Rule, Change Workflow, Change Documentation and Compliance Templates, plus 2 more sections
  • Calls python3

What it does

Pyats Config Mgmt is an agent skill from automateyournetwork/netclaw. Direct, pyATS-based network change management - pre-change baselines, configuration deployment, post-change verification, rollback procedures, and compliance validation. Use when pushing config to a device, planning a network change, rolling back a configuration, or running compliance checks outside of a governed workflow platform. When the change should go through Itential's golden-config/compliance engine instead, use itential-automation.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Regulatory compliance. The repository describes itself as: An AI agent that claws through your network. The licence is Apache-2.0.

When your agent uses it

  • Pushing config to a device
  • Planning a network change
  • Rolling back a configuration
  • Running compliance checks outside of a governed workflow platform

Example prompts

  • “/pyats-config-mgmt”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Pre-Change Baseline
  2. Plan the Change
  3. Apply Configuration
  4. Post-Change Verification
  5. Rollback (If Needed)

What it can do on your machine

Read from SKILL.md and the folder at commit aa90e7d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pyats Config Mgmt loads about 3k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 694 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~116
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from automateyournetwork/netclaw at commit aa90e7d, republished under its Apache-2.0 licence (© automateyournetwork). 694 words, ~3,005 tokens.

Download SKILL.mdSave it as .claude/skills/pyats-config-mgmt/SKILL.md (or your agent's skills folder).
name
pyats-config-mgmt
description
Direct, pyATS-based network change management - pre-change baselines, configuration deployment, post-change verification, rollback procedures, and compliance validation. Use when pushing config to a device, planning a network change, rolling back a configuration, or running compliance checks outside of a governed workflow platform. When the change should go through Itential's golden-config/compliance engine instead, use `itential-automation`.
license
Apache-2.0
user-invocable
true

Configuration Management

Golden Rule

NEVER apply configuration without first capturing a baseline. If the change goes wrong, you need to know what to roll back to.

Change Workflow

Phase 1: Pre-Change Baseline

Capture the current state of everything the change might affect.

1A: Save Running Configuration
bash
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_show_running_config '{"device_name":"R1"}'

Store this output — it is the rollback reference.

1B: Capture Relevant State

Depending on the change type, capture the appropriate state:

For interface changes:

bash
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_run_show_command '{"device_name":"R1","command":"show ip interface brief"}'

PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_run_show_command '{"device_name":"R1","command":"show interfaces"}'

For routing changes:

bash
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_run_show_command '{"device_name":"R1","command":"show ip route"}'

PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_run_show_command '{"device_name":"R1","command":"show ip ospf neighbor"}'

PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_run_show_command '{"device_name":"R1","command":"show ip bgp summary"}'

For ACL/security changes:

bash
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_run_show_command '{"device_name":"R1","command":"show ip access-lists"}'
1C: Connectivity Baseline

Ping critical targets before the change:

bash
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_ping_from_network_device '{"device_name":"R1","command":"ping 8.8.8.8 repeat 10"}'
Phase 2: Plan the Change

Before applying any config, explicitly state:

  1. What config lines will be applied
  2. Why each line is needed
  3. What the expected effect is
  4. What could go wrong (risk assessment)
  5. How to verify success
  6. How to rollback if it fails
Phase 3: Apply Configuration
bash
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_configure_device '{"device_name":"R1","config_commands":["interface Loopback99","ip address 99.99.99.99 255.255.255.255","description NetClaw-Managed","no shutdown"]}'

Configuration best practices:

  • Apply one logical change at a time (don't batch unrelated changes)
  • Do NOT include configure terminal or end — the tool handles this
  • DO include exit when changing config context (e.g., exiting an interface)
  • Use descriptive descriptions on interfaces and route-maps
  • For complex changes (route-maps, ACLs), build the complete object before applying to an interface

Common configuration patterns:

Interface configuration:

json
["interface GigabitEthernet2", "description WAN-Link-to-ISP", "ip address 203.0.113.1 255.255.255.252", "no shutdown"]

OSPF configuration:

json
["router ospf 1", "router-id 1.1.1.1", "network 10.0.0.0 0.0.255.255 area 0", "passive-interface default", "no passive-interface GigabitEthernet1"]

BGP configuration:

json
["router bgp 65001", "neighbor 10.1.1.2 remote-as 65002", "neighbor 10.1.1.2 description ISP-Peer", "address-family ipv4 unicast", "neighbor 10.1.1.2 activate", "neighbor 10.1.1.2 route-map ISP-IN in", "neighbor 10.1.1.2 route-map ISP-OUT out", "exit-address-family"]

ACL configuration:

json
["ip access-list extended MGMT-ACCESS", "permit tcp 10.0.0.0 0.0.0.255 any eq 22", "permit tcp 10.0.0.0 0.0.0.255 any eq 443", "deny ip any any log"]

Route-map configuration:

json
["route-map ISP-IN permit 10", "match ip address prefix-list ALLOWED-IN", "set local-preference 200", "exit", "route-map ISP-IN deny 99"]

Static route:

json
["ip route 0.0.0.0 0.0.0.0 203.0.113.2 name DEFAULT-TO-ISP"]

NTP configuration:

json
["ntp server 10.0.0.1 prefer", "ntp server 10.0.0.2", "ntp source Loopback0"]
Phase 4: Post-Change Verification

Immediately after applying config, verify:

4A: Check for Errors in Logs
bash
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_show_logging '{"device_name":"R1"}'

Look for new error messages that appeared after the change timestamp.

4B: Verify the Config Was Applied
bash
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_show_running_config '{"device_name":"R1"}'

Compare with the pre-change config to confirm only intended changes were made.

4C: Verify Expected State

Re-run the same show commands from Phase 1B and compare:

  • Are routing adjacencies still up?
  • Are the expected new routes present?
  • Are interface states correct?
  • Are ACL counters incrementing as expected?
4D: Connectivity Verification

Re-ping all targets from Phase 1C:

bash
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_ping_from_network_device '{"device_name":"R1","command":"ping 8.8.8.8 repeat 10"}'

Compare success rate and RTT with baseline.

Phase 5: Rollback (If Needed)

If verification fails, roll back by applying the inverse configuration:

To remove added config:

json
["no interface Loopback99"]

To restore changed config: Apply the original configuration lines from the Phase 1A baseline.

For complex rollbacks, apply the entire relevant section from the saved running config.

After rollback, re-verify that the device returned to its baseline state.

Change Documentation

After every change, produce a change report:

Change Report — YYYY-MM-DD HH:MM UTC
Device: R1 (devnetsandboxiosxec8k.cisco.com)
Requestor: [who requested the change]

Change Description:
  Added Loopback99 (99.99.99.99/32) for OSPF router-id migration

Config Applied:
  interface Loopback99
   ip address 99.99.99.99 255.255.255.255
   description OSPF-RID-Migration
   no shutdown

Pre-Change State:
  - Routing table: 47 routes
  - OSPF neighbors: 2 (FULL)
  - Connectivity: 100% to 8.8.8.8

Post-Change State:
  - Routing table: 48 routes (+1 connected 99.99.99.99/32)
  - OSPF neighbors: 2 (FULL) — no change
  - Connectivity: 100% to 8.8.8.8 — no change
  - New log entries: %LINEPROTO-5-UPDOWN: Loopback99 up/up

Verification: PASSED
Rollback Required: No

Compliance Templates

Minimum Security Baseline (Apply to Every New Device)
json
[
  "service timestamps debug datetime msec localtime",
  "service timestamps log datetime msec localtime",
  "service password-encryption",
  "no ip source-route",
  "no ip http server",
  "ip http secure-server",
  "ip ssh version 2",
  "ip ssh time-out 60",
  "ip ssh authentication-retries 3",
  "login on-failure log",
  "login on-success log",
  "banner login ^ Authorized access only. All activity is monitored. ^"
]
VTY Hardening
json
[
  "line vty 0 4",
  "transport input ssh",
  "exec-timeout 15 0",
  "login local",
  "exit",
  "line vty 5 15",
  "transport input ssh",
  "exec-timeout 15 0",
  "login local"
]
Show full SKILL.md (309 more words)Show less

ServiceNow Change Request Integration (MISSION02 Enhancement)

Policy selection comes from AGENTS.md: an API-created Terminal Intent Local/Lab record for explicitly authorized lab endpoints uses local approval/audit instead of ServiceNow/mandatory GAIT. This exception is not inferred from an environment variable or missing credentials. Read-only preparation, real baseline and rollback artifacts, an API APPLY PHASE and verification remain required. Never evade an actual tool-level denial with another transport. All other requests follow the production change policy below.

When ServiceNow is available ($SERVICENOW_MCP_SCRIPT is set), every configuration change MUST be gated by an approved Change Request.

Pre-Change: Create CR

Before any config push, create a Change Request:

bash
python3 $MCP_CALL "python3 -u $SERVICENOW_MCP_SCRIPT" create_change_request '{"short_description":"Configure SSH hardening on R1","description":"Apply VTY line hardening: SSH-only transport, exec timeout 15 min, login local. Affects R1 management plane.","category":"Network","priority":"3","risk":"low","impact":"low"}'
Submit for Approval
bash
python3 $MCP_CALL "python3 -u $SERVICENOW_MCP_SCRIPT" submit_change_for_approval '{"change_number":"CHG0012345"}'
Approval Gate

Check if the CR is approved before proceeding:

bash
python3 $MCP_CALL "python3 -u $SERVICENOW_MCP_SCRIPT" get_change_request_details '{"change_number":"CHG0012345"}'

STOP if state is not "Approved". Inform the human and wait.

Pre-Change Check: No Open P1/P2

Verify no open Priority 1 or 2 incidents on affected CIs:

bash
python3 $MCP_CALL "python3 -u $SERVICENOW_MCP_SCRIPT" list_incidents '{"urgency":"1","state":"open"}'

If P1/P2 incidents exist on affected devices, do NOT proceed. Escalate to human.

Post-Change: Close or Escalate CR

If verification passes:

bash
python3 $MCP_CALL "python3 -u $SERVICENOW_MCP_SCRIPT" update_change_request '{"change_number":"CHG0012345","updates":{"state":"closed","close_code":"successful","close_notes":"Change applied and verified. Post-change baseline matches expected state."}}'

If verification fails:

bash
python3 $MCP_CALL "python3 -u $SERVICENOW_MCP_SCRIPT" update_change_request '{"change_number":"CHG0012345","updates":{"state":"review","close_notes":"Post-change verification FAILED. Rollback initiated. Human review required."}}'
Emergency Changes

For emergency changes (network outage, security incident):

  1. Notify human immediately
  2. Create CR with category "Emergency"
  3. Proceed with change (approval gate bypassed)
  4. CR must be retroactively approved within 24 hours

GAIT Audit Trail

Record every phase of the change in GAIT:

bash
python3 $MCP_CALL "python3 -u $GAIT_MCP_SCRIPT" gait_record_turn '{"user_text":"Example only: replace with the actual authorized request.","assistant_text":"Config change on R1: Phase 1 baseline captured. Phase 2 plan approved. Phase 3 config applied. Phase 4 verification PASSED. ServiceNow CR CHG0012345 closed successful.","artifacts":[]}'

The 5-phase workflow with GAIT creates an immutable record:

  1. Baseline → GAIT commit with pre-change state
  2. Plan → GAIT commit with change plan and CR number
  3. Apply → GAIT commit with exact commands pushed
  4. Verify → GAIT commit with post-change state and diff
  5. Document → GAIT commit with final summary and CR closure

Audit examples are illustrative. Replace request, outcomes, identifiers and counts with observed session evidence; do not record these example results as facts. Inspect MCP isError, returned ok, and the recorded turn with gait_show when validating a new client/schema. Follow gait-session-tracking for branch checkout.

© automateyournetwork, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in workspace/skills/pyats-config-mgmt of automateyournetwork/netclaw.

Open the folder on GitHubat commit aa90e7d

Compare with similar skills

Pyats Config Mgmt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pyats Config Mgmt compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pyats Config Mgmt this skillautomateyournetwork/netclaw676—~3kAutomated safety check: PassApache-2.0
Implementing Azure Defender For Cloudmukul975/Anthropic-Cybersecurity-Skills34k—~3.1kAutomated safety check: PassApache-2.0
Validator Expertjeremylongshore/tons-of-skills-marketplace2.8k—~1.9kAutomated safety check: PassMIT
AWS Cloudformationaws/agent-toolkit-for-aws2.8k—~3.6kAutomated safety check: PassApache-2.0
Performing Container Security Scanning With Trivymukul975/Anthropic-Cybersecurity-Skills34k—~818Automated safety check: PassApache-2.0
Scanning Docker Images With Trivymukul975/Anthropic-Cybersecurity-Skills34k—~1.9kAutomated safety check: WarnApache-2.0

Similar skills

  • Implementing Azure Defender For Cloud

    mukul975/Anthropic-Cybersecurity-Skills

    Enable Microsoft Defender for Cloud (CSPM + CWPP) across VMs, containers, SQL, storage, and Key Vault, using Azure Policy for evaluation, Log Analytics for telemetry, Azure Arc for hybrid coverage…

    34k GitHub stars~3.1k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • Validator Expert

    jeremylongshore/tons-of-skills-marketplace

    Validate production readiness of Vertex AI Agent Engine deployments across security, monitoring, performance, compliance, and best practices.

    2.8k GitHub stars~1.9k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • AWS Cloudformation

    aws/agent-toolkit-for-aws

    Official

    Authors, validates, and troubleshoots AWS CloudFormation templates.

    2.8k GitHub stars~3.6k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Performing Container Security Scanning With Trivy

    mukul975/Anthropic-Cybersecurity-Skills

    Runs Trivy across every target type it supports - container images, filesystems, Git repositories, and Kubernetes clusters - for OS and dependency vulnerabilities, IaC misconfiguration, exposed…

    34k GitHub stars~818 tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • Scanning Docker Images With Trivy

    mukul975/Anthropic-Cybersecurity-Skills

    Scans a Docker image with Trivy for vulnerabilities in OS packages and language dependencies, misconfiguration, exposed secrets, and licence violations, emitting SARIF, CycloneDX, or SPDX output.

    34k GitHub stars~1.9k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check: warnings
  • Sca Trivy

    AgentSecOps/SecOpsAgentKit

    Software Composition Analysis (SCA) and container vulnerability scanning using Aqua Trivy for identifying CVE vulnerabilities in dependencies, container images, IaC misconfigurations, and license…

    220 GitHub starsUsed in 2 repos~3.7k tokens
    SecurityAuto-check passed

More from automateyournetwork/netclaw

All 120 skills in this repo
  • EVE-NG Lab Topology Design

    automateyournetwork/netclaw

    Entry point for designing EVE-NG network labs: classifies the request, gathers missing requirements, proposes options and validates the resulting topology.

    677 GitHub stars~612 tokensUpdated today
    Auto-check passed
  • ACI Policy Change Deployment

    automateyournetwork/netclaw

    Deploys Cisco ACI policy changes only behind an approved ServiceNow Change Request, capturing pre and post-change fault baselines and rolling back automatically on a fault delta.

    677 GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Cisco ACI Fabric Health Audit

    automateyournetwork/netclaw

    Runs a phased health audit of a Cisco ACI fabric through MCP tools: node status, links, tenant and policy review, faults and endpoint learning.

    677 GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Anta Validation

    automateyournetwork/netclaw

    Validate Arista EOS network state against ANTA's pre-built 208-test catalogue, with structured pass/fail verdicts.

    677 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Arista Cvp

    automateyournetwork/netclaw

    Arista CloudVision Portal (CVP) automation via REST API — device inventory, events, connectivity monitoring, tag management (4 tools).

    677 GitHub stars~2.2k tokensUpdated today
    Auto-check: notes
  • AWS Cloud Monitoring

    automateyournetwork/netclaw

    AWS CloudWatch monitoring — metrics, alarms, log queries, VPC flow log analysis, network performance.

    677 GitHub stars~1k tokensUpdated today
    Auto-check passed

Questions about Pyats Config Mgmt

What does Pyats Config Mgmt do?

Direct, pyATS-based network change management - pre-change baselines, configuration deployment, post-change verification, rollback procedures, and compliance validation. Pyats Config Mgmt is an agent skill from automateyournetwork/netclaw. Direct, pyATS-based network change management - pre-change baselines, configuration deployment, post-change verification, rollback procedures, and compliance validation.

When should I use Pyats Config Mgmt?

Pyats Config Mgmt fits situations like: pushing config to a device; planning a network change; rolling back a configuration; running compliance checks outside of a governed workflow platform.

How do I install Pyats Config Mgmt in Claude Code?

Run `npx skills add automateyournetwork/netclaw --skill pyats-config-mgmt -a claude-code`. Or copy the skill folder (workspace/skills/pyats-config-mgmt in automateyournetwork/netclaw) into .claude/skills/pyats-config-mgmt in your project. Claude Code loads it when a task matches its description.

How do I install Pyats Config Mgmt in Codex?

Run `npx skills add automateyournetwork/netclaw --skill pyats-config-mgmt -a codex`. Or copy the skill folder (workspace/skills/pyats-config-mgmt in automateyournetwork/netclaw) into .agents/skills/pyats-config-mgmt in your project. Codex loads it when a task matches its description.

Can I use Pyats Config Mgmt in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add automateyournetwork/netclaw --skill pyats-config-mgmt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pyats-config-mgmt, .gemini/skills/pyats-config-mgmt, .github/skills/pyats-config-mgmt and .opencode/skills/pyats-config-mgmt in your project.

What does Pyats Config Mgmt need to run?

Going by SKILL.md and its folder, Pyats Config Mgmt needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Pyats Config Mgmt access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pyats Config Mgmt safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pyats Config Mgmt use?

Pyats Config Mgmt is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pyats Config Mgmt use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pyats Config Mgmt?

Skills that share tags, products or a category with Pyats Config Mgmt: Implementing Azure Defender For Cloud (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Validator Expert (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), AWS Cloudformation (aws/agent-toolkit-for-aws, 2.8k stars) and Performing Container Security Scanning With Trivy (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pyats Config Mgmt?

automateyournetwork (a GitHub user) maintains it in automateyournetwork/netclaw, which has 676 GitHub stars. The repository holds 120 skills in this directory. The repository was last updated on October 9, 2026.

Source: automateyournetwork/netclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.