opencode-config/AGENTS.md

Global Rules

Orchestrator Model

• Main chat = planning ONLY. All research, commands, edits, implementation — ONLY via subagents.
• Never do yourself: filesystem research, grep/glob, bash commands, file edits, tests, git ops.
• Maximum: high-level plan + reports to user + delegation to task subagents.
• Pipeline: delegate each phase (ISSUE → IMPLEMENT → DOCS → CI → REVIEW → MERGE → MEMORY) to a subagent.
• Subagent error → 1 retry, then STOP + report.

Pipeline

Pipeline: ISSUE → IMPLEMENT → DOCS → CI → REVIEW → MERGE → MEMORY. pipeline-status = read-only oracle (NEXT action). merge-pr = orchestrator-safe merge wrapper. Execution via /run-pipeline skill.

Bug Discovery Protocol

If a bug is found outside current task scope — load skill bug-discovery.

Linear Execution

• Within a single repository — strictly linear pipeline execution.
• Cannot start a second pipeline until the first is complete (merge or close).
• Issues are created by ONE agent at a time (batch creation), not parallel agents.
• Parallel research (explore agents, 3-4 concurrently) — allowed.
• Parallel execution (implementation/review/docs) — PROHIBITED.
• Reason: agents jump between branches → conflicts, lost work, chaos.

Read Path

Before starting a task in a repo: scan filenames in docs/handoff/ (if any) — open relevant ones by topic.

Code Style

• Follow existing conventions in the repo
• Load code-standards skill for detailed rules
• No comments unless explicitly requested
• Match surrounding code style (imports, naming, patterns)

Tools

Use tools instead of bash. On failure — STOP + report. Deny-list in permission.bash of opencode.json.

Language

• Always respond to the user in Russian.