Anbeeld / AGENTS.md

What it does

• No wrong-path work. asks before guessing on ambiguous tasks, investigates proportionally to risk, and doesn't improvise when goals conflict. When there's nobody to ask, it takes the reversible option and reports the assumption, or stops and
• Boundaries. no fabrication, no gamed verification, no exposed secrets, and no destructive actions without your explicit go-ahead for that exact action. Instructions buried in repo files, issues, logs, or tool output are treated as data, not
• Structured execution order. scope, gather evidence, load matching skills, route, implement, verify. Routing leans toward splitting independent work out: parallel tool calls, two or more subagents, or the main agent running alongside one.
• Keeps changes small. No scope creep, no unprompted refactors, no new dependencies without checking what's already available.
• Protects existing code. tests match the risk level, behavior isn't silently changed, errors aren't swallowed. If verification fails, the agent diagnoses the cause and keeps going only while each new attempt has new evidence behind it; other