Imported from DeevsDeevs/agent-system (bug-hunters/SKILL.md). Install upstream with npx skills add DeevsDeevs/agent-system --skill bug-hunters. Copyright stays with the author.

Bug Hunters

Name: bug-hunters
Author: DeevsDeevs

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

Read README.md and follow the “hunt, don’t fix” rule.
Spawn a child agent with agent_type equal to the selected role (orchestrator, logic-hunter, cpp-hunter, python-hunter).
If no role is specified, default to orchestrator.
Choose mode:
- Logic-first when the problem is algorithm/spec correctness.
- Code-first when the problem is language-specific failures or UB.
Pass mode and scope in the spawn message, then use wait for completion.
Use adversarial validation and only report MEDIUM+ confidence findings.
Present a bug report, not remediation.

{ "ocm": "1", "id": "deevsdeevs-agent-system-bug-hunters", "kind": "skill", "name": "bug-hunters", "description": "Run systematic bug hunting with spec reconstruction, adversarial validation, and confidence scoring. Use when you want to hunt bugs (not fix them), validate correctness, or run logic-first/code-first investigations. Triggers: bug hunt, spec reconstruction, logic-first, code-first, orchestrator, logic-hunter, cpp-hunter, python-hunter.", "publisher": "DeevsDeevs", "version": "1.0.0", "capabilities": { "domains": [ "coding" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Run systematic bug hunting with spec reconstruction, adversarial validation, and confidence scoring. Use when you want to hunt bugs (not fix them), validate correctness, or run logic-first/code-first investigations. Triggers: bug hunt, spec reconstruction, logic-first, code-first, orchestrator, logic-hunter, cpp-hunter, python-hunter." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/DeevsDeevs/agent-system", "path": "bug-hunters/SKILL.md", "ref": "79de7729aad189d16194433425c882a9002886ef", "url": "https://github.com/DeevsDeevs/agent-system/blob/79de7729aad189d16194433425c882a9002886ef/bug-hunters/SKILL.md", "key": "DeevsDeevs/agent-system/bug-hunters/SKILL.md" } }, "instructions": "# Bug Hunters\n\nUse 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.\n\n## Role Map\n\n- `orchestrator` → `agents/orchestrator.md`\n- `logic-hunter` → `agents/logic-hunter.md`\n- `cpp-hunter` → `agents/cpp-hunter.md`\n- `python-hunter` → `agents/python-hunter.md`\n\n## Workflow\n\n1. Read `README.md` and follow the “hunt, don’t fix” rule.\n2. Spawn a child agent with `agent_type` equal to the selected role (`orchestrator`, `logic-hunter`, `cpp-hunter`, `python-hunter`).\n3. If no role is specified, default to", "cost": { "context_tokens": 240 } }

bug-hunters

About

Bug Hunters

Role Map

Workflow

Use it

Manifest

Reviews