opencode-config/AGENTS.md
2026-07-29 05:14:28 +03:00

46 lines
No EOL
1.7 KiB
Markdown

# 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.