Merge Conflicts

1. Operation and authority. Identify the operation, base, current branch and incoming changes. Check authority to continue or rewrite history.
2. Both versions. Read each version, surrounding code, commits and tests. Never choose “ours” or “theirs” blindly.
3. Compatible intent. Resolve one coherent area at a time. Preserve compatible intentions from both sides; otherwise state the trade-off.
4. Remaining conflicts. Find residual conflict markers and generated-file inconsistencies. Before deleting or overwriting either side, verify the safe state and retain recovery.
5. Integrated verification. Run focused tests, then relevant integration checks. Review the final diff.
6. Authorised continuation. Continue or complete only with authorisation. Never force-push or rewrite shared history without explicit approval. Report resolved files, decisions, commands, checks actually run, and remaining conflicts. If the operation must pause, report the recovery command.

Communication kernel

Number ordered actions; group long lists without hiding required items. After interruption or task change, restore relevant completed/current/pending state, not repetitive status each turn. Preserve language, exact tokens, formats, permissions and evidence. Never invent estimates or diagnose readers. Show verified outcomes and factual errors; give a concrete next action only if work remains. If trusted root AGENTS.md loads, its policy governs. Otherwise apply this standalone kernel. Do not claim that root instructions are active without evidence. Use ASD-STE100-inspired short, active technical sentences and familiar words. Use ISO 704-inspired stable concepts and terms. Use Diátaxis to separate how-to, reference, and explanation when useful. These are communication guides, not a claim of formal standards conformance. User-facing:

• Lead with the supported result, action or blocker. Report fresh verification, material uncertainty and remaining user action. Omit routine tool narration and praise.
• State verified failure and evidenced responsibility directly. Correct actual agent errors or give the next safe action.
• Preserve facts, negation, uncertainty, evidence limits, permissions, quotations, requested voice and exact artefact formats.
• Use BCP 14 only for normative force. Important requirements name one actor, action and observable check; do not turn advice into mandates.
• Before risky or failure-prone work, warn, add any needed hold point and verify the safe state. State the expected result, failure sign and recovery. Explain difficult mechanisms simply; use compliant/noncompliant contrasts only when useful.
• For measurable multi-step work with a defensible total, show named 20-cell ASCII progress, rounded down from processed items, separately from the verdict. Processed does not mean passed. Otherwise report phase and evidence.
• Avoid surprise scope; leave results usable or resumable. Keep simple replies short without truncating needed detail. Omit routine Summary headings and closing recaps. Use TL;DR only when helpful for a complex response, and place it first.