MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Review a HaloPSA / HaloITSM asset (Device) with its related tickets and CMDB/CI relationships — read-only.
Install Halo Asset Context
$ npx skills add automateyournetwork/netclaw --skill halo-asset-context -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install automateyournetwork/netclaw halo-asset-context --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/halo-asset-context .claude/skills/halo-asset-context && 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 "halo-asset-context" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/halo-asset-context into .claude/skills/halo-asset-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "halo-asset-context", 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/halo-asset-contextType 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 halo-asset-context -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install automateyournetwork/netclaw halo-asset-context --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/halo-asset-context .agents/skills/halo-asset-context && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "halo-asset-context" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/halo-asset-context into .agents/skills/halo-asset-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "halo-asset-context", 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 halo-asset-context -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install automateyournetwork/netclaw halo-asset-context --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/halo-asset-context .cursor/skills/halo-asset-context && 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 "halo-asset-context" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/halo-asset-context into .cursor/skills/halo-asset-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "halo-asset-context", 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/halo-asset-context--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 halo-asset-context -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install automateyournetwork/netclaw halo-asset-context --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/halo-asset-context .gemini/skills/halo-asset-context && 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 "halo-asset-context" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/halo-asset-context into .gemini/skills/halo-asset-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "halo-asset-context", 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 halo-asset-contextInstalls 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 halo-asset-context -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/halo-asset-context .github/skills/halo-asset-context && 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 "halo-asset-context" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/halo-asset-context into .github/skills/halo-asset-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "halo-asset-context", 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 halo-asset-context -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 halo-asset-context --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/halo-asset-context .opencode/skills/halo-asset-context && 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 "halo-asset-context" agent skill from https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/halo-asset-context into .opencode/skills/halo-asset-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "halo-asset-context", 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.
Facts
- Skill name
halo-asset-context- GitHub stars
- 676
- Token cost
- ~1.8k tokens
- SKILL.md length
- 782 words
- Files
- 1
- Skills in repo
- 120
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Review a HaloPSA / HaloITSM asset (Device) with its related tickets and CMDB/CI relationships — read-only.
- Works in 5 steps: Locate the asset. If you only have a… → Read the asset detail → Pull its related tickets (the core step) → …
- Investigating a Halo asset
- SKILL.md covers MCP Server, Available Tools, Key Concepts and Workflow, plus 4 more sections
- Calls python3; needs HALO_CLIENT_SECRET
What it does
Halo Asset Context is an agent skill from automateyournetwork/netclaw. Review a HaloPSA / HaloITSM asset (Device) with its related tickets and CMDB/CI relationships — read-only. Use when investigating a Halo asset, checking a device's ticket history, mapping CI dependencies, or gathering asset context before a change.
Its SKILL.md is about 1.8k 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 Agent Workflows. It works with Model Context Protocol and Python. The repository describes itself as: An AI agent that claws through your network. The licence is Apache-2.0.
When your agent uses it
- Investigating a Halo asset
- Checking a devices ticket history
- Mapping CI dependencies
- Gathering asset context before a change
Example prompts
- “/halo-asset-context”
Requirements
- Python 3
- A credential in HALO_CLIENT_SECRET
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Locate the asset. If you only have a description or partial name, search first
- Read the asset detail
- Pull its related tickets (the core step)
- Map its CMDB/CI relationships
- Report an asset-context summary: identity, owning client/site, open vs historical tickets, notable recurring issues, and CI dependencies…
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 these keys or tokens, usually read from environment variables:
HALO_CLIENT_SECRET
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Halo Asset Context loads about 1.8k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 782 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.
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). 782 words, ~1,798 tokens.
Download SKILL.mdSave it as
.claude/skills/halo-asset-context/SKILL.md (or your agent's skills folder).- name
- halo-asset-context
- description
- Review a HaloPSA / HaloITSM asset (Device) with its related tickets and CMDB/CI relationships — read-only. Use when investigating a Halo asset, checking a device's ticket history, mapping CI dependencies, or gathering asset context before a change.
- license
- Apache-2.0
- user-invocable
- true
Halo Asset Context
Review an asset in Halo together with the tickets and CMDB/CI relationships around it — entirely read-only. Halo is HaloPSA / HaloITSM (the same product and REST API); assets are called "Devices" in Halo's API vocabulary. Use this to build a full operational picture of a device before acting on it, correlating its history and dependencies.
MCP Server
- Server:
halo-mcp(NetClaw-authored,mcp-servers/halo-mcp/) - Command:
python3 -u mcp-servers/halo-mcp/halo_mcp_server.py(stdio transport) - Auth: OAuth2 client-credentials —
HALO_CLIENT_ID/HALO_CLIENT_SECRETagainstHALO_BASE_URL - Python: 3.10+ · Dependencies:
fastmcp,httpx,python-dotenv - Read/write posture: The whole server is read-only except one gated write (
halo_create_change_request, in the halo-change-request skill). Every tool in this skill is read-only and makes no changes to Halo.
Available Tools
| Tool | Parameters | What It Does |
|---|---|---|
halo_list_assets | customer?, assettype_id?, search? | List/search assets ("Devices"), optionally scoped by customer, asset type, or free text |
halo_get_asset | asset (name / inventory-number / id) | Read one asset — detail, fields, and ticket counts |
halo_get_asset_tickets | asset, open_only? | List the tickets related to an asset — the core context tool |
halo_get_asset_relationships | asset | An asset's CMDB/CI hierarchy and relationship context |
halo_list_clients | search? | Resolve a Halo Client name to its id (the customer param) |
halo_list_sites | customer?, search? | Narrow to a site within a client |
Key Concepts
- Halo == HaloPSA == HaloITSM. Same API for both editions.
- Assets are "Devices."
halo_list_assets/halo_get_assetaccept an asset name, inventory number, or numeric id — you do not need the id up front. - The Halo "Client" is the customer. Scope asset queries to an org with the
customerparam (a client name or id); the server resolves it to aclient_id. In an MSP (HaloPSA) tenant this is essential to avoid crossing client boundaries. - Two context dimensions: tickets (what has gone wrong / changed on this device) via
halo_get_asset_tickets, and relationships (what this device depends on or supports) viahalo_get_asset_relationships. Use both for a complete picture. - Read-only. Nothing here writes to Halo. If the review concludes a change is needed, hand off to halo-change-request.
Workflow
Review an asset and everything around it:
Locate the asset. If you only have a description or partial name, search first:
halo_list_assets(customer="<client>", search="<name/serial/model>")Scope by
customer(the Halo Client) in multi-client tenants to disambiguate.Read the asset detail:
halo_get_asset(asset="<name / inventory number / id>")Note its type, key fields, owning client/site, and ticket counts.
Pull its related tickets (the core step):
halo_get_asset_tickets(asset="<asset>") # all history halo_get_asset_tickets(asset="<asset>", open_only=true) # active issues onlyLook for recurring faults, recent changes, and open work.
Map its CMDB/CI relationships:
halo_get_asset_relationships(asset="<asset>")Understand upstream dependencies and downstream impact before anyone touches it.
Report an asset-context summary: identity, owning client/site, open vs historical tickets, notable recurring issues, and CI dependencies — plus a recommendation (e.g. "raise a change via halo-change-request" or "no action").
Show full SKILL.md (356 more words)Show less
Integration with Other Skills
| Skill | Integration |
|---|---|
| gait-session-tracking | Mandatory. Record every asset/ticket/relationship query in the GAIT audit trail |
| halo-change-request | Hand off here when the review concludes a change is warranted — pass the affected asset into the asset param |
| halo-ticket-context | Drill into any individual ticket surfaced by halo_get_asset_tickets for its full action history |
| nautobot-sot / netbox-reconcile | Cross-reference Halo's asset record against the network source of truth; ticket any drift |
| memory | Recall prior findings about the same device across sessions |
Environment Variables
| Variable | Required | Description |
|---|---|---|
HALO_BASE_URL | Yes | Halo host, e.g. https://<tenant>.halopsa.com |
HALO_CLIENT_ID | Yes | OAuth2 client-credentials application id |
HALO_CLIENT_SECRET | Yes | OAuth2 client secret |
HALO_TENANT | Optional | Tenant identifier |
HALO_SCOPE | Optional | OAuth2 scope (default all) |
HALO_AUTH_URL | Optional | Override the auth-server URL for self-hosted layouts |
HALO_VERIFY_SSL | Optional | true/false TLS verification (default true) |
HALO_TIMEOUT | Optional | Per-request timeout in seconds (default 30) |
HALO_PAGE_SIZE / HALO_MAX_PAGES | Optional | Pagination tuning (defaults 50 / 20) |
HALO_RATE_LIMIT | Optional | Requests/minute cap (0 = disabled) |
Important Rules
- Read-only skill. None of these tools change Halo. The only write in the entire
halo-mcpserver ishalo_create_change_request(halo-change-request skill). - Scope by the Halo Client. Pass the customer org via the
customerparam to keep queries inside client boundaries — critical in MSP (HaloPSA) tenants. - Assets resolve by name, inventory number, or id — no need to look up the numeric id first.
- Halo == HaloPSA == HaloITSM — identical behavior for both editions.
- GAIT logging is mandatory for all queries.
- Escalate, don't mutate. If the context implies a change, route it through halo-change-request (preview -> confirm -> submit); never try to write from this skill.
Failure Behavior
- If a tool call fails with an authentication or connection error, check that
HALO_BASE_URL,HALO_CLIENT_ID,HALO_CLIENT_SECRETare set and valid before assuming a data or device problem. - On a tool error (timeout, unreachable host, malformed response), report the failure and its error message directly to the user rather than fabricating or guessing at results.
- For a confirmed read-only call, check connectivity and retry once if appropriate. For any call that changes state or sends a message, a timeout does not prove the action failed: inspect current state or delivery status before retrying, preserve the required approval/change gates, and do not repeat an action whose outcome is unknown.
© 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/halo-asset-context of automateyournetwork/netclaw.
Open the folder on GitHubat commit aa90e7d
Compare with similar skills
Halo Asset Context 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 |
|---|---|---|---|---|---|---|
| Halo Asset Context this skillautomateyournetwork/netclaw | 676 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MemPalace Setup and OperationMemPalace/mempalace | 60k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Google Antigravity SDKgoogle-antigravity/antigravity-sdk-python | 3.7k | — | ~2.1k | Automated safety check: Notes | Apache-2.0 | |
| FastmcpTommy-yw/RunbookHermes | 546 | 3 repos | ~2.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
MemPalace Setup and Operation
MemPalace/mempalace
Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.
Google Antigravity SDK
google-antigravity/antigravity-sdk-python
Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK.
Fastmcp
Tommy-yw/RunbookHermes
Build, test, inspect, install, and deploy MCP servers with FastMCP in Python.
Fastmcp Client CLI
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
More from automateyournetwork/netclaw
All 120 skills in this repoEVE-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.
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.
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.
Anta Validation
automateyournetwork/netclaw
Validate Arista EOS network state against ANTA's pre-built 208-test catalogue, with structured pass/fail verdicts.
Arista Cvp
automateyournetwork/netclaw
Arista CloudVision Portal (CVP) automation via REST API — device inventory, events, connectivity monitoring, tag management (4 tools).
AWS Cloud Monitoring
automateyournetwork/netclaw
AWS CloudWatch monitoring — metrics, alarms, log queries, VPC flow log analysis, network performance.
Related
Works with
Categories
Questions about Halo Asset Context
What does Halo Asset Context do?
Review a HaloPSA / HaloITSM asset (Device) with its related tickets and CMDB/CI relationships — read-only. Halo Asset Context is an agent skill from automateyournetwork/netclaw. Review a HaloPSA / HaloITSM asset (Device) with its related tickets and CMDB/CI relationships — read-only.
When should I use Halo Asset Context?
Halo Asset Context fits situations like: investigating a Halo asset; checking a devices ticket history; mapping CI dependencies; gathering asset context before a change.
How do I install Halo Asset Context in Claude Code?
Run `npx skills add automateyournetwork/netclaw --skill halo-asset-context -a claude-code`. Or copy the skill folder (workspace/skills/halo-asset-context in automateyournetwork/netclaw) into .claude/skills/halo-asset-context in your project. Claude Code loads it when a task matches its description.
How do I install Halo Asset Context in Codex?
Run `npx skills add automateyournetwork/netclaw --skill halo-asset-context -a codex`. Or copy the skill folder (workspace/skills/halo-asset-context in automateyournetwork/netclaw) into .agents/skills/halo-asset-context in your project. Codex loads it when a task matches its description.
Can I use Halo Asset Context 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 halo-asset-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/halo-asset-context, .gemini/skills/halo-asset-context, .github/skills/halo-asset-context and .opencode/skills/halo-asset-context in your project.
What does Halo Asset Context need to run?
Going by SKILL.md and its folder, Halo Asset Context needs the command-line tools its instructions call (python3) and credentials named HALO_CLIENT_SECRET. Our summary lists: Python 3; A credential in HALO_CLIENT_SECRET.
Does Halo Asset Context 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 Halo Asset Context 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 Halo Asset Context use?
Halo Asset Context 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 Halo Asset Context use?
About 1.8k tokens (SKILL.md is roughly 7.2k 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 Halo Asset Context?
Skills that share tags, products or a category with Halo Asset Context: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MemPalace Setup and Operation (MemPalace/mempalace, 60k stars) and Google Antigravity SDK (google-antigravity/antigravity-sdk-python, 3.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Halo Asset Context?
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.