devops by automateyournetwork
Network Path Analysis with gtrace automateyournetwork/gtrace-path-analysis
Network path tracing and monitoring — traceroute with MPLS/ECMP/NAT detection, continuous MTR monitoring, and distributed GlobalPing probes from 500+ worldwide locations.
What it changes View full report → Passed 5 of 11 test cases with the skill, and 2 of 11 without it.
Without skill 18%
With skill 45%
Checks it passed that the model alone missed and 3 more in the full report
6 fixed4 passed either way12 still failing0 broke
Pass-rate lift +27 pp
Tokens +25%
Agent turns 0%
Response time -35% Model gemini-3.6-flashMeasured 8/16/2026 v1 10 of 22 cases passed with skill · 11 comparable
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/automateyournetwork-gtrace-path-analysis/SKILL.md https://app.decimal.ai/s/automateyournetwork-gtrace-path-analysis/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add automateyournetwork-gtrace-path-analysis, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/automateyournetwork-gtrace-path-analysis/ and pins it in .decimal/skills.lock
$ decimalai skills add automateyournetwork-gtrace-path-analysisCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/automateyournetwork-gtrace-path-analysis/SKILL.md https://app.decimal.ai/s/automateyournetwork-gtrace-path-analysis/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt A traceroute to web host 93.184.216.34 revealed packet loss at hop 4. Execute a continuous monitoring check sending 100 probe rounds to confirm if this drop is persistent.
What was checked, without and with the skill Checked Without skill With skill Executes python3 $MCP_CALL "gtrace mcp" mtr '{"target":"93.184.216.34","count":100}'
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 107 lines single file
Network Path Analysis with gtrace
How to Call the gtrace MCP Tools
python3 $MCP_CALL "gtrace mcp" TOOL_NAME '{"param":"value"}'
When to Use
Trace the path between two endpoints and identify each hop (router, latency, loss)
Detect MPLS labels, ECMP load balancing, and NAT translation points along the path
Monitor a path continuously with MTR to identify intermittent packet loss or latency spikes
Run distributed traceroutes from 500+ GlobalPing probe locations worldwide to compare paths from different vantage points
Verify transit providers, peering, and routing policy by inspecting AS-level path data
Troubleshoot asymmetric routing, suboptimal paths, or blackholes
Available Tools
Workflow: Path Troubleshooting
When asked "why is traffic slow to X?" or "trace the path to X":
Step 1: Traceroute
Run an advanced traceroute to see every hop, latency, and any MPLS/ECMP/NAT indicators.
python3 $MCP_CALL "gtrace mcp" traceroute '{"target":"8.8.8.8"}'
For IPv6:
When it activates Automatically, when a task matches.
Use when tracing the path to a destination, diagnosing slow network routes, detecting MPLS or ECMP load balancing, running MTR for intermittent packet loss, or testing reachability from global vantage points.
Track record Benchmark 5 / 11
test cases passed, vs 2 / 11 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported automateyournetwork / netclaw
workspace/skills/gtrace-path-analysis/SKILL.md
View on GitHub ↗ License Apache-2.0Imported 8/3/2026Version v1