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 automateyournetwork/netclaw --skill humanrail-escalationgit clone --depth 1 https://github.com/automateyournetwork/netclawWrote 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/automateyournetwork/netclaw/humanrail-escalation)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/humanrail-escalation"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/humanrail-escalation/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/automateyournetwork/netclaw/humanrail-escalation"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/humanrail-escalation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 55 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 317 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00088 | $0.03299 |
| Opus 5 | $0.00044 | $0.01649 |
| Sonnet 5 | $0.00018 | $0.00660 |
| Haiku 4.5 | $0.00009 | $0.00330 |
Grade A, and why
humanrail-escalation scanned grade A with 0 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 9d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HumanRail Escalation
Safety — Non-Negotiable Rules
NEVER route tasks that expose internal tooling or infrastructure details to workers. HumanRail workers are external humans. Task descriptions must be neutral: describe the decision needed without referencing agent names, internal hostnames, file paths, or credentials. Frame the task as a domain question a knowledgeable engineer would answer — not as "an AI agent needs help."
NEVER use HumanRail as a substitute for ServiceNow Change Management. A HumanRail approval is an engineering judgment call, not a formal ITSM change record. Pre-destructive approvals via HumanRail are a second safety layer — the ServiceNow CR must still exist and be in Implement state before any config push.
NEVER expose PII, device credentials, or configuration secrets in task payloads. Sanitize payloads: use device roles ("core router") not hostnames, use interface descriptions not IP addresses where possible.
ALWAYS wait for verified status before acting. A task with status submitted has been answered by a worker but not yet verified. Only act on the output when status == "verified".
When to Use
| Situation | Use HumanRail | Use ServiceNow CR | Use Slack Escalation |
|---|---|---|---|
| Agent confidence low — multiple valid interpretations | ✓ | — | — |
| Pre-destructive op beyond normal ITSM gating | ✓ | Required (both) | — |
| Ambiguous incident ticket needs triage | ✓ | — | Notify after |
| P1/P2 in-flight, need immediate human judgment | ✓ | — | ✓ (both) |
| Standard config change with approved CR | — | ✓ | — |
| Routine maintenance window | — | ✓ | — |
| Auto-quarantine endpoint (ISE) | — | — | ✓ (ise-incident-response) |
MCP Server
| Property | Value |
|---|---|
| Source | prime001/humanrail-mcp-server |
| Transport | Streamable HTTP (FastMCP, default port 8100) |
| Language | Python 3.10+ |
| Tools | 7 (create_task, get_task, wait_for_task, cancel_task, list_tasks, get_usage, health_check) |
| Auth | HUMANRAIL_API_KEY (Bearer token — ek_live_... or ek_test_...) |
| Public endpoint | https://humanrail.dev/mcp (no local install required) |
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.
- 9d ago First seen · 318 lines · 88 tokens per session scan A 4169874fb3f1
humanrail-escalation is a skill published in the GitHub repository automateyournetwork/netclaw (657 stars, last pushed 6d ago), licensed Apache-2.0. It adds 88 tokens to every session and 3,299 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…