Menu
Initialize a threat hunting case from a signal, detection, intel lead, or analyst suspicion
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Show available THRUNT threat hunting commands and artifact layout
Map available telemetry, query surfaces, tenants, retention windows, and investigation blind spots
Initialize a threat hunting program with an environment map, tool inventory, huntmap, and empty execution directories
Create phase plans for a threat hunt with exact telemetry tasks, receipts, and query outputs
Publish a hunt as a case report, escalation, detection promotion, or leadership summary
Execute a hunt phase with parallel telemetry work, query logging, receipt generation, and optional wave targeting
| name | hunt-new-case |
| description | Initialize a threat hunting case from a signal, detection, intel lead, or analyst suspicion |
| argument-hint | [--auto] [--pack <id>] |
| allowed-tools | Read, Bash, Write, Task, AskUserQuestion |
These hunt-native artifacts are the source of truth for the case.
Creates:
.planning/config.json.planning/MISSION.md.planning/HYPOTHESES.md.planning/SUCCESS_CRITERIA.md.planning/HUNTMAP.md.planning/STATE.md.planning/QUERIES/.planning/RECEIPTS/Bootstrap should only scaffold the case. Do not seed sample queries, sample receipts, or completed phases.
Unknown scope details, data sources, operators, and constraints must remain TBD unless the operator confirms them.
Confirmed bootstrap facts such as the case name, mode, opened date, and initial phase/status must be filled immediately.
After this command: Run /hunt-shape-hypothesis or /hunt-plan 1.
<execution_context> @.github/thrunt-god/workflows/hunt-bootstrap.md @.github/thrunt-god/templates/config.json @.github/thrunt-god/templates/mission.md @.github/thrunt-god/templates/hypotheses.md @.github/thrunt-god/templates/success-criteria.md @.github/thrunt-god/templates/huntmap.md @.github/thrunt-god/templates/hunt-state.md </execution_context>
Execute the bootstrap workflow from @.github/thrunt-god/workflows/hunt-bootstrap.md in case mode. Focus on turning the input signal into a scoped case with explicit hypotheses, data sources, and evidence requirements. When `--pack ` is present, use the pack bootstrap output as the default case skeleton and ask only for the missing pack parameters or signal-specific overrides. Create `.planning/QUERIES/` and `.planning/RECEIPTS/` as empty directories only. Do not load query-log or receipt templates during bootstrap; those belong to `/hunt-run` after real execution begins. Default behavior is scaffold-first: write confirmed facts only and leave unknown values as `TBD` instead of inventing sample content. Create `.planning/config.json` during bootstrap if it does not already exist so runtime, settings, and connector commands are immediately usable. Never hand-write `.planning/config.json`; use `thrunt-tools config-new-program` and `thrunt-tools config-set` so the file stays valid THRUNT config. Use built-in connector ids exactly as the runtime registers them, for example `splunk` and `elastic`; do not substitute `elasticsearch`. When writing connector profiles, use `base_url` for the runtime URL field; do not invent or substitute `endpoint`. Only configure connector profiles when auth type and secret ref names are confirmed. Never invent placeholder env vars or placeholder secrets for blocked connectors. When writing `secret_refs`, each confirmed secret must use the THRUNT object shape `{ "type": "env", "value": "ENV_VAR_NAME" }` rather than a raw string. Keep connector narrative, status notes, and access commentary in `ENVIRONMENT.md`, not in ad hoc config keys. Do not leave bootstrap-known fields as `TBD` after writing the files. Write the hunt artifacts directly.