Hig Project Context
raintree-technology/hig-doctor
Create or update a shared Apple design context document that other HIG skills use to tailor guidance.
Catalyst Center device inventory and site management - list/filter devices by hostname, IP, platform, family, role, reachability; view site hierarchy; get interface details per device; device…
$ npx skills add automateyournetwork/netclaw --skill catc-inventory -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install automateyournetwork/netclaw catc-inventory --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workspace/skills/catc-inventory .claude/skills/catc-inventory && rm -rf skills-srcUse ~/.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/
Install the "catc-inventory" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/catc-inventory into .claude/skills/catc-inventory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catc-inventory", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/catc-inventoryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add automateyournetwork/netclaw --skill catc-inventory -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install automateyournetwork/netclaw catc-inventory --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/workspace/skills/catc-inventory .agents/skills/catc-inventory && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "catc-inventory" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/catc-inventory into .agents/skills/catc-inventory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catc-inventory", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add automateyournetwork/netclaw --skill catc-inventory -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install automateyournetwork/netclaw catc-inventory --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/workspace/skills/catc-inventory .cursor/skills/catc-inventory && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "catc-inventory" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/catc-inventory into .cursor/skills/catc-inventory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catc-inventory", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/automateyournetwork/netclaw.git --path workspace/skills/catc-inventory--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add automateyournetwork/netclaw --skill catc-inventory -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install automateyournetwork/netclaw catc-inventory --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/workspace/skills/catc-inventory .gemini/skills/catc-inventory && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "catc-inventory" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/catc-inventory into .gemini/skills/catc-inventory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catc-inventory", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install automateyournetwork/netclaw catc-inventoryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add automateyournetwork/netclaw --skill catc-inventory -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/workspace/skills/catc-inventory .github/skills/catc-inventory && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "catc-inventory" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/catc-inventory into .github/skills/catc-inventory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catc-inventory", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add automateyournetwork/netclaw --skill catc-inventory -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install automateyournetwork/netclaw catc-inventory --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/automateyournetwork/netclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/workspace/skills/catc-inventory .opencode/skills/catc-inventory && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "catc-inventory" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/catc-inventory into .opencode/skills/catc-inventory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "catc-inventory", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
catc-inventoryCatalyst Center device inventory and site management - list/filter devices by hostname, IP, platform, family, role, reachability; view site hierarchy; get interface details per device; device…
Catc Inventory is an agent skill from automateyournetwork/netclaw. Catalyst Center device inventory and site management - list/filter devices by hostname, IP, platform, family, role, reachability; view site hierarchy; get interface details per device; device reachability monitoring; cross-reference with pyATS. Use when listing network devices, checking device reachability, auditing software versions, viewing site hierarchy, or finding a device by serial number. This is a narrow, purpose-built tool for that pyATS cross-reference workflow specifically. For anything else in…
Its SKILL.md is about 4.5k 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 Mobile. It works with iOS. The repository describes itself as: An AI agent that claws through your network. The licence is Apache-2.0.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit aa90e7d. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
python3From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Catc Inventory loads about 4.5k tokens when it runs. Until then it costs about 171 tokens; SKILL.md has 965 words of instructions outside code blocks.
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.
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.
The full file from automateyournetwork/netclaw at commit aa90e7d, republished under its Apache-2.0 licence (© automateyournetwork). 965 words, ~4,481 tokens.
.claude/skills/catc-inventory/SKILL.md (or your agent's skills folder).All Catalyst Center tool calls use this invocation pattern:
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 -u $CATC_MCP_SCRIPTVariable shorthand used throughout this document:
CATC_CMD="CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 -u $CATC_MCP_SCRIPT"Use the $MCP_CALL protocol handler to invoke MCP tools:
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" TOOL_NAME 'ARGS_JSON'fetch_devices -- List and Filter Network DevicesFetches devices from the /dna/intent/api/v1/network-device endpoint with extensive filtering. NEVER call this tool without at least one filter parameter -- unfiltered queries can return massive result sets and are blocked by design.
Parameters (all optional, but at least one required):
| Parameter | Type | Description |
|---|---|---|
hostname | List[str] | Filter by device hostname(s) |
managementIpAddress | List[str] | Filter by management IP(s) |
serialNumber | List[str] | Filter by serial number(s) |
platformId | List[str] | Filter by platform ID (e.g., C9300-48UXM) |
family | List[str] | Filter by device family (e.g., Switches and Hubs, Routers, Wireless Controller) |
type | List[str] | Filter by device type (e.g., Cisco Catalyst 9300 Switch) |
role | List[str] | Filter by role: ACCESS, DISTRIBUTION, CORE, BORDER ROUTER, UNKNOWN |
reachabilityStatus | List[str] | Filter by: Reachable, Unreachable |
collectionStatus | List[str] | Filter by: Managed, Partial Collection Failure, Could Not Synchronize |
softwareVersion | List[str] | Filter by IOS/NX-OS version string |
softwareType | List[str] | Filter by: IOS-XE, NX-OS, IOS, AireOS |
series | List[str] | Filter by product series (e.g., Cisco Catalyst 9300 Series Switches) |
locationName | List[str] | Filter by full site path (e.g., Global/USA/Building1/Floor1) |
associatedWlcIp | List[str] | For APs: filter by WLC management IP |
macAddress | List[str] | Filter by device MAC address(es) |
id | List[str] | Filter by device UUID(s) |
roleSource | List[str] | Filter by role source: MANUAL, AUTO |
offset | str | Starting record for pagination (e.g., "0") |
limit | str | Maximum records to return (e.g., "50") |
sortBy | str | Attribute to sort by (e.g., hostname) |
sortOrder | str | asc or desc |
Response fields per device: id (UUID), hostname, managementIpAddress, macAddress, serialNumber, platformId, softwareVersion, softwareType, type, family, series, role, roleSource, reachabilityStatus, collectionStatus, errorCode, locationName, location, upTime, lastUpdated, lastUpdateTime, associatedWlcIp, apManagerInterfaceIp, and more.
fetch_sites -- List All SitesFetches the complete site hierarchy from Catalyst Center. Takes no arguments.
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_sites '{}'Response fields per site: id, name, parentId, siteNameHierarchy (full path like Global/USA/NYC/Floor2), type (area, building, floor), address, latitude, longitude.
fetch_interfaces -- Get Interfaces for a DeviceFetches all interfaces for a specific device by its UUID from the /dna/intent/api/v1/interface/network-device/{device_id} endpoint.
Parameters:
device_id (string, required): The UUID of the device (obtained from fetch_devices response id field)CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_interfaces '{"device_id":"a1b2c3d4-e5f6-7890-abcd-ef1234567890"}'Response fields per interface: id, deviceId, portName, interfaceType, adminStatus, status (operStatus), speed, duplex, ipv4Address, ipv4Mask, macAddress, mediaType, mtu, vlanId, nativeVlanId, description, portMode, lastUpdated, and more.
Identify devices that Catalyst Center cannot reach -- critical for outage detection.
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"reachabilityStatus":["Unreachable"]}'Analyze the results:
lastUpdated to determine when the device was last seencollectionStatus for additional context (Could Not Synchronize vs Partial Collection Failure)locationName to determine if the outage is site-localizedEscalation: If multiple devices at the same site are unreachable, this likely indicates a site-wide outage (WAN link, upstream switch, power). Escalate to the site-wide outage triage workflow in the catc-troubleshoot skill.
Enumerate all switching devices managed by Catalyst Center.
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"family":["Switches and Hubs"]}'Refine by role:
# Access layer switches only
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"family":["Switches and Hubs"],"role":["ACCESS"]}'
# Distribution layer switches
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"family":["Switches and Hubs"],"role":["DISTRIBUTION"]}'
# Core switches
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"family":["Switches and Hubs"],"role":["CORE"]}'Refine by platform:
# All Catalyst 9300 series
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"series":["Cisco Catalyst 9300 Series Switches"]}'
# Specific platform ID
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"platformId":["C9300-48UXM"]}'CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"family":["Routers"]}'# Wireless LAN Controllers
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"family":["Wireless Controller"]}'
# Unified Access Points
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"family":["Unified AP"]}'
# APs associated with a specific WLC
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"associatedWlcIp":["10.1.100.10"]}'This is a two-step process: first find the device to obtain its UUID, then query interfaces.
Step 1: Find the device
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"hostname":["CORE-SW-01"]}'Extract the id field (UUID) from the response.
Step 2: Fetch interfaces using the UUID
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_interfaces '{"device_id":"a1b2c3d4-e5f6-7890-abcd-ef1234567890"}'Analyze interface data:
adminStatus (UP vs DOWN) and status (operationally UP vs DOWN)adminStatus=UP but status=down -- these are operationally failed interfacesspeed and duplex for mismatchesportModeBuild a report of devices organized by site hierarchy.
Step 1: Retrieve the site hierarchy
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_sites '{}'Step 2: For each site, retrieve devices at that location
# Devices at a specific site
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"locationName":["Global/USA/NYC/Floor2"]}'Build the report:
Site Inventory Report
=====================
Catalyst Center: $CCC_HOST
Timestamp: YYYY-MM-DD HH:MM UTC
Global/USA/NYC
Global/USA/NYC/Floor1 (floor)
+--------------+------------------+-----------+------------+--------+
| Hostname | Mgmt IP | Platform | SW Version | Status |
+--------------+------------------+-----------+------------+--------+
| ACC-SW-01 | 10.1.10.1 | C9300-48U | 17.09.04a | Reach |
| ACC-SW-02 | 10.1.10.2 | C9300-48U | 17.09.04a | Reach |
| AP-NYC-F1-01 | 10.1.10.100 | C9120AXI | 17.09.04a | Reach |
+--------------+------------------+-----------+------------+--------+
Global/USA/NYC/Floor2 (floor)
+--------------+------------------+-----------+------------+--------+
| Hostname | Mgmt IP | Platform | SW Version | Status |
+--------------+------------------+-----------+------------+--------+
| ACC-SW-03 | 10.1.20.1 | C9300-24P | 17.09.04a | Reach |
| AP-NYC-F2-01 | 10.1.20.100 | C9130AXI | 17.09.04a | Unrch |
+--------------+------------------+-----------+------------+--------+
Total: 5 devices | 4 reachable | 1 unreachableIdentify devices running non-compliant or mixed firmware versions.
# Find all devices on a specific software version
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"softwareVersion":["17.09.04a"]}'
# Find devices running IOS-XE
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"softwareType":["IOS-XE"]}'Audit steps:
softwareVersionSoftware Version Audit
======================
Platform: Cisco Catalyst 9300 Series Switches
17.09.04a: 42 devices (APPROVED)
17.06.05 : 3 devices (NON-COMPLIANT -- schedule upgrade)
17.03.04a: 1 device (EOL VERSION -- immediate upgrade required)
Platform: Cisco Catalyst 9800 Wireless Controller
17.09.04a: 2 devices (APPROVED)# By serial number
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"serialNumber":["FDO2325A0B1"]}'
# By management IP
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"managementIpAddress":["10.1.10.1"]}'
# By MAC address
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"macAddress":["00:1A:2B:3C:4D:5E"]}'Devices with collection failures may have partial data in Catalyst Center.
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"collectionStatus":["Partial Collection Failure"]}'CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"collectionStatus":["Could Not Synchronize"]}'Common causes:
When the pyATS testbed is available ($PYATS_MCP_SCRIPT and $PYATS_TESTBED_PATH are set), cross-reference Catalyst Center inventory with live device data for deeper validation.
Compare what Catalyst Center reports vs what the device itself reports:
# Catalyst Center says the device runs 17.09.04a
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_devices '{"hostname":["CORE-SW-01"]}'
# Verify directly from the device
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_run_show_command '{"device_name":"CORE-SW-01","command":"show version"}'Flag any discrepancy -- this indicates Catalyst Center inventory is stale and needs a resync.
Compare Catalyst Center interface data vs live device state:
# Catalyst Center interface data (may be up to 25 minutes stale)
CCC_HOST=$CCC_HOST CCC_USER=$CCC_USER CCC_PWD=$CCC_PWD python3 $MCP_CALL "python3 -u $CATC_MCP_SCRIPT" fetch_interfaces '{"device_id":"<UUID>"}'
# Live interface state from the device
PYATS_TESTBED_PATH=$PYATS_TESTBED_PATH python3 $MCP_CALL "${PYATS_PYTHON:-python3} -u $PYATS_MCP_SCRIPT" pyats_run_show_command '{"device_name":"CORE-SW-01","command":"show ip interface brief"}'Identify drift: Interfaces that show UP in Catalyst Center but DOWN on the live device (or vice versa) indicate a polling lag or inventory desync.
Always produce a consolidated inventory summary when performing audit workflows:
Catalyst Center Inventory Report
=================================
Controller: $CCC_HOST
Timestamp: YYYY-MM-DD HH:MM UTC
Device Summary
--------------
Total Devices: 156
Switches and Hubs: 92 (59%)
Routers: 12 (8%)
Wireless Controller: 4 (3%)
Unified AP: 48 (31%)
Reachability
------------
Reachable: 152 (97.4%)
Unreachable: 4 (2.6%)
- ACC-SW-15 (10.1.30.15) at Global/USA/NYC/Floor3 -- last seen 2h ago
- AP-CHI-F2-03 (10.2.20.103) at Global/USA/CHI/Floor2 -- last seen 45m ago
- AP-CHI-F2-04 (10.2.20.104) at Global/USA/CHI/Floor2 -- last seen 45m ago
- RTR-WAN-02 (10.0.0.2) at Global/USA/NYC/MDF -- last seen 6h ago
Collection Status
-----------------
Managed: 150
Partial Collection Failure: 4
Could Not Synchronize: 2
Role Distribution
-----------------
ACCESS: 82 | DISTRIBUTION: 8 | CORE: 4 | BORDER ROUTER: 2 | UNKNOWN: 12
Site Summary
------------
Total Sites: 24 (8 areas, 10 buildings, 6 floors)
Sites with unreachable devices: 2 (Global/USA/NYC/Floor3, Global/USA/CHI/Floor2)
Software Version Compliance
----------------------------
IOS-XE 17.09.04a: 140 devices (COMPLIANT)
IOS-XE 17.06.05: 8 devices (NON-COMPLIANT)
AireOS 8.10.185: 4 devices (COMPLIANT)
NX-OS 10.3(2): 4 devices (COMPLIANT)After completing any inventory operation, record the session in GAIT:
python3 $MCP_CALL "python3 -u $GAIT_MCP_SCRIPT" gait_record_turn '{"user_text":"Example only: replace with the actual authorized request.","assistant_text":"Catalyst Center inventory audit on $CCC_HOST: 156 devices total, 152 reachable (97.4%), 4 unreachable (ACC-SW-15, AP-CHI-F2-03, AP-CHI-F2-04, RTR-WAN-02). Collection failures: 6 devices. Software compliance: 96% on approved versions. 2 sites with unreachable devices flagged for investigation.","artifacts":[]}'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
Just SKILL.md in workspace/skills/catc-inventory of automateyournetwork/netclaw.
Open the folder on GitHubat commit aa90e7d
Catc Inventory 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Catc Inventory this skillautomateyournetwork/netclaw | 676 | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Hig Project Contextraintree-technology/hig-doctor | 143 | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Hig Components Contentraintree-technology/hig-doctor | 143 | 5 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Discover iOS KeysPoomSmart/MGKeys | 238 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Argent Metro Debuggerbbplayer-app/BBPlayer | 1.2k | — | ~3.4k | Automated safety check: Pass | MIT | |
| iOS Simulator Skilln0an/VivaDicta | 130 | 1 repos | ~2.5k | Automated safety check: Pass | MIT |
raintree-technology/hig-doctor
Create or update a shared Apple design context document that other HIG skills use to tailor guidance.
raintree-technology/hig-doctor
Apple Human Interface Guidelines for content display components.
PoomSmart/MGKeys
Discover and map new MobileGestalt keys for a new iOS version in MGKeys.
bbplayer-app/BBPlayer
Debug a JS runtime via CDP using argent debugger tools. An agent skill from bbplayer-app/BBPlayer.
n0an/VivaDicta
21 production-ready scripts for iOS app testing, building, and automation.
Code-with-Beto/skills
Scaffold a unified, cross-platform color theme system into an Expo Router app.
automateyournetwork/netclaw
Entry point for designing EVE-NG network labs: classifies the request, gathers missing requirements, proposes options and validates the resulting topology.
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.
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.
automateyournetwork/netclaw
Validate Arista EOS network state against ANTA's pre-built 208-test catalogue, with structured pass/fail verdicts.
automateyournetwork/netclaw
Arista CloudVision Portal (CVP) automation via REST API — device inventory, events, connectivity monitoring, tag management (4 tools).
automateyournetwork/netclaw
AWS CloudWatch monitoring — metrics, alarms, log queries, VPC flow log analysis, network performance.
Works with
Categories
Catalyst Center device inventory and site management - list/filter devices by hostname, IP, platform, family, role, reachability; view site hierarchy; get interface details per device; device…. Catc Inventory is an agent skill from automateyournetwork/netclaw. Catalyst Center device inventory and site management - list/filter devices by hostname, IP, platform, family, role, reachability; view site hierarchy; get interface details per device; device reachability monitoring; cross-reference with pyATS.
Catc Inventory fits situations like: listing network devices; checking device reachability; auditing software versions; viewing site hierarchy.
Run `npx skills add automateyournetwork/netclaw --skill catc-inventory -a claude-code`. Or copy the skill folder (workspace/skills/catc-inventory in automateyournetwork/netclaw) into .claude/skills/catc-inventory in your project. Claude Code loads it when a task matches its description.
Run `npx skills add automateyournetwork/netclaw --skill catc-inventory -a codex`. Or copy the skill folder (workspace/skills/catc-inventory in automateyournetwork/netclaw) into .agents/skills/catc-inventory in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add automateyournetwork/netclaw --skill catc-inventory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/catc-inventory, .gemini/skills/catc-inventory, .github/skills/catc-inventory and .opencode/skills/catc-inventory in your project.
Going by SKILL.md and its folder, Catc Inventory needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
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.
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.
Catc Inventory 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.
About 4.5k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Catc Inventory: Hig Project Context (raintree-technology/hig-doctor, 143 stars), Hig Components Content (raintree-technology/hig-doctor, 143 stars), Discover iOS Keys (PoomSmart/MGKeys, 238 stars) and Argent Metro Debugger (bbplayer-app/BBPlayer, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
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.