# Deevsdeevs Agent System Bug Hunters > Bug Hunters - Skill: `tomevault-io/deevsdeevs-agent-system-bug-hunters` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/deevsdeevs-agent-system-bug-hunters` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/deevsdeevs-agent-system-bug-hunters/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/deevsdeevs-agent-system-bug-hunters --- # Bug Hunters Use a single skill with role selection. If the user specifies a hunter, use that role; otherwise start with the orchestrator and ask which mode applies. ## Role Map - `orchestrator` → `agents/orchestrator.md` - `logic-hunter` → `agents/logic-hunter.md` - `cpp-hunter` → `agents/cpp-hunter.md` - `python-hunter` → `agents/python-hunter.md` ## Workflow 1. Read `README.md` and follow the “hunt, don’t fix” rule. 2. Spawn a child agent with `agent_type` equal to the selected role (`orchestrator`, `logic-hunter`, `cpp-hunter`, `python-hunter`). 3. If no role is specified, default to `orchestrator`. 4. Choose mode: - Logic-first when the problem is algorithm/spec correctness. - Code-first when the problem is language-specific failures or UB. 5. Pass mode and scope in the spawn message, then use `wait` for completion. 6. Use adversarial validation and only report MEDIUM+ confidence findings. 7. Present a bug report, not remediation. --- > Converted and distributed by [TomeVault](https://tomevault.io/claim/deevsdeevs) — claim your Tome and manage your conversions.