workspace/skills/batfish-config-analysis/SKILL.md
Batfish network configuration analysis -- pre-deployment validation, reachability testing, ACL/firewall tracing, differential analysis, compliance checking. Use when validating configs before deployment, testing traffic paths, tracing ACL rules, comparing config versions, or auditing compliance policies. Strictly read-only.
npx skillsauth add automateyournetwork/netclaw batfish-config-analysisInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
python3 -u mcp-servers/batfish-mcp/batfish_mcp_server.py (stdio transport)BATFISH_HOST and BATFISH_PORT environment variablespybatfish, mcp[cli], python-dotenv| Tool | Parameters | What It Does |
|------|-----------|--------------|
| batfish_upload_snapshot | snapshot_name, configs/config_path, network | Upload device configs to Batfish and create a named snapshot |
| batfish_validate_config | snapshot_name, network | Validate configs with per-device pass/fail status, vendor detection, warnings |
| batfish_test_reachability | snapshot_name, src_ip, dst_ip, protocol, dst_port | Test if traffic can flow between two endpoints with full path trace |
| batfish_trace_acl | snapshot_name, device, filter_name, src_ip, dst_ip, protocol, dst_port | Trace a packet through ACL rules to find matching permit/deny rule |
| batfish_diff_configs | reference_snapshot, candidate_snapshot, include_routes, include_reachability | Compare two snapshots for route and reachability differences |
| batfish_check_compliance | snapshot_name, policy_type | Check configs against compliance policies (6 built-in policy types) |
| batfish_list_snapshots | network | List all available snapshots |
| batfish_delete_snapshot | snapshot_name, network | Delete a snapshot |
When a user wants to validate configurations before deployment:
batfish_upload_snapshot with inline configs dict or path to config directorybatfish_validate_config to check parse status, vendor detection, warnings/errorsbatfish_test_reachability for critical traffic pathsbatfish_check_compliance against organizational policies# Upload proposed configs
batfish_upload_snapshot snapshot_name="pre-change-site-a" config_path="/path/to/configs/"
# Validate parse status
batfish_validate_config snapshot_name="pre-change-site-a"
# Test critical path
batfish_test_reachability snapshot_name="pre-change-site-a" src_ip="10.1.1.1" dst_ip="10.2.2.1" protocol="TCP" dst_port=443
# Check compliance
batfish_check_compliance snapshot_name="pre-change-site-a" policy_type="interface_descriptions"
When comparing before/after configurations:
batfish_upload_snapshot with current configsbatfish_upload_snapshot with proposed configsbatfish_diff_configs to find route and reachability differencesbatfish_trace_acl on any newly denied trafficWhen investigating access control issues:
batfish_upload_snapshot with device configsbatfish_trace_acl with device, ACL name, and packet headers| Skill | Integration | |-------|-------------| | pyats-config-mgmt | Validate configs with Batfish before pushing via pyATS | | gait-session-tracking | All Batfish operations automatically logged | | servicenow-change-workflow | Reference Batfish validation in change request evidence | | fwrule-analyzer | Complement ACL trace with cross-vendor overlap analysis | | cml-lab-lifecycle | Validate CML lab configs with Batfish analysis |
docker ps | grep batfish)batfish_list_snapshots to see available snapshotsbatfish_validate_config to list devices in snapshotBATFISH_HOST -- Batfish hostname (default: localhost)BATFISH_PORT -- Batfish port (default: 9997)BATFISH_NETWORK -- Default network name (default: netclaw)testing
Human-in-the-loop escalation via HumanRail — route low-confidence agent decisions, pre-destructive operation approvals, and ambiguous incident tickets to real human engineers. Human answers are verified and returned as structured output. Workers are paid via Lightning Network. Use when the agent is uncertain, when a destructive change needs explicit human sign-off beyond a ServiceNow CR, or when an ambiguous ticket requires human triage before automated handling.
testing
Manage EVE-NG node lifecycle. Use when listing nodes, checking runtime state, creating or deleting nodes, starting or stopping nodes or whole labs, verifying node details, or wiping node NVRAM back to factory defaults.
development
Manage EVE-NG labs and platform inventory. Use when listing labs, checking lab metadata, creating or deleting labs, importing or exporting lab archives, checking EVE-NG health or auth, or verifying available node images before build work.
tools
Execute live CLI commands on running EVE-NG nodes over telnet console. Use when running show commands, making live config changes, verifying protocol state, testing connectivity, checking console readiness, or interacting with IOS, Junos, VPCS, EOS, or NX-OS nodes.