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 forwardgit 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/forward)<a href="https://agentmods.dev/skills/automateyournetwork/netclaw/forward"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/forward/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/forward"><img src="https://agentmods.dev/badge/skills/automateyournetwork/netclaw/forward.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 107 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00041 | $0.03223 |
| Opus 5 | $0.00020 | $0.01612 |
| Sonnet 5 | $0.00008 | $0.00645 |
| Haiku 4.5 | $0.00004 | $0.00322 |
Grade A, and why
forward 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 — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forward Skill
Skill: /forward
MCP Server: forward-mcp
Source: https://github.com/forwardnetworks/forward-mcp
Use When
Use this skill for Forward snapshot assurance, collection, and analysis:
- Discover Forward networks, snapshots, and devices
- Verify paths and reachability
- Discover and run NQE checks
- Review predefined checks, failed checks, and vulnerability analysis
- Compare NQE, snapshot, and config diffs
- Search configurations
- Analyze blast radius for a source location to destination IPv4 subnets
- Review hardware and OS lifecycle support
- Find missing devices inferred during collection
- Support lab or real-network collection workflows
Startup
- Start with
get_default_settingsto see configured defaults. - If no default network is set, use
list_networkswith a small limit and ask the user which network to use. - Prefer explicit
network_idandsnapshot_idvalues for repeatable results. - Use bounded limits by default. Use
all_resultsonly when the user needs the complete dataset. - In Forward SaaS, prefer
FORWARD_API_BASE_URL=https://fwd.appand setFORWARD_INSTANCE_IDfor local cache partitioning when multiple SaaS orgs or accounts are used on the same NetClaw host.
Tool Routing
| User intent | Preferred tools |
|---|---|
| "List Forward networks" | list_networks |
| "Use this network by default" | set_default_network |
| "Show collection sources" | list_classic_devices, get_classic_device |
| "Add lab devices" | upsert_classic_devices |
| "Show collector status" | get_collector_status |
| "Start collection" | start_collection_task, get_collector_task, then wait_for_latest_snapshot; use start_collection only for legacy flows |
| "Show snapshots" | list_snapshots, get_latest_snapshot |
| "List devices" | list_devices, get_device_basic_info |
| "Find missing collection neighbors" | get_missing_devices |
| "Trace paths" | search_paths_bulk, then search_paths for one-off traces |
| "Trace app-aware paths" | list_l7_applications, then search_paths_bulk or search_paths with app_id, url, or domain |
| "Show blast radius" | suggest_blast_radius_sources, then get_blast_radius |
| "Find NQE checks" | search_nqe_queries, list_nqe_queries |
| "Run an NQE check" | run_nqe_query_by_id; use start_nqe_query for long-running checks |
| "Write or run ad-hoc NQE" | Prefer search_nqe_queries first; use run_nqe_query only when no built-in query fits and async NQE for long-running or large results |
| "Show predefined checks" | list_predefined_checks |
| "Show failed checks or intent status" | list_checks, then get_check |
| "Show vulnerabilities or CVE exposure" | search_nqe_queries, then run_nqe_query_by_id with the /Security/CVEs/... query IDs |
| "Draw topology from Forward" | get_snapshot_topology, then search NQE for CDP/LLDP and protocol-peer evidence when needed |
| "Summarize large results" | get_nqe_result_summary, get_nqe_result_chunks, analyze_nqe_result_sql |
| "Search configs" | search_configs |
| "Compare NQE or intent/check results" | get_nqe_diff |
| "Summarize snapshot diffs" | get_snapshot_diff_summary |
| "Show route, ACL, NAT, interface, check, or vulnerability diffs" | get_snapshot_diff |
| "Compare snapshots/configs" | get_config_diff |
| "Check hardware or OS support" | get_device_hardware, get_hardware_support, get_os_support |
| "Show locations" | list_locations, get_device_locations |
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 · 309 lines · 41 tokens per session scan A 59c8e7ca353e
forward is a skill published in the GitHub repository automateyournetwork/netclaw (657 stars, last pushed 6d ago), licensed Apache-2.0. It adds 41 tokens to every session and 3,223 once invoked, about $0.0002 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
bitcoin-auth-diagnostics
Diagnose and troubleshoot bitcoin-auth token generation and verification issues. This skill should be used when users encounter authentication failures, signature verification errors, or integration problems with the bitcoin-auth library.
chrome-devtools
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.