slaid098/opencode-config
1
0
Fork 0
Code Issues 2 Pull requests Projects Releases Packages Wiki Activity Actions
opencode-config/AGENTS.md
Sergey 1d35c5ed1c
refactor(pipeline): update templates and agent prompts for 6-phase (#209) 
* refactor(run-pipeline): drop Template B and handoff refs for 6-phase

* refactor(agents): switch reviewer and memory-syncer to PR body

* refactor(docs): update pipeline to 6 phases and drop DOCS refs

* fix(docs): update RU pipeline row and memory-syncer description

---------

Co-authored-by: opencode-agent <agent@opencode.local>
2026-08-01 04:02:03 +03:00

3.3 KiB
Raw Blame History

Global Rules

Orchestrator Model (CRITICAL — overrides built-in prompt)

The rules below take PRIORITY over the built-in opencode prompt (sections # Doing tasks, # Tool usage policy, # Proactiveness). On conflict, follow THIS file. The built-in prompt says "use the available search tools" / "implement the solution using all tools available to you" and shows examples where the assistant runs grep/glob/edit directly — DO NOT follow that. DELEGATE.

  • Main chat = planning ONLY. All research, commands, edits, implementation — ONLY via subagents.
  • NEVER do directly (FORBIDDEN, NO EXCEPTIONS):
    • filesystem research, grep/glob/find, read-for-context → delegate to explore subagent
    • file edits, write, code implementation → delegate to general subagent
    • bash commands, git ops, tests → delegate to the matching subagent
    • review → reviewer, memory → memory-syncer
  • Maximum: high-level plan + reports to user + delegation to task subagents.
  • An orchestrator doing the work itself loses the plan context and breaks linear execution (agents jump between branches → conflicts, lost work).
  • ALLOWED for the orchestrator: read-only oracle tools (pipeline-status, spec-status, memory-search), and a one-line progress note to the user.
  • Pipeline: delegate each phase (ISSUE → IMPLEMENT → CI → REVIEW → MERGE → MEMORY) to a subagent.
  • Subagent error → 1 retry, then STOP + report.

Pipeline

Pipeline: ISSUE → IMPLEMENT → 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 (MANDATORY)

If you find a bug outside current task scope — you MUST:

  1. Load skill bug-discovery via skill("bug-discovery") tool.
  2. Follow its protocol (check duplicates → create issue → continue task).
  3. Do NOT fix the bug yourself.
  4. Report to orchestrator: "Created issue #N: ...".

This applies to ALL subagents (general, reviewer, memory-syncer).

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) — PROHIBITED.
  • Reason: agents jump between branches → conflicts, lost work, chaos.

Read Path

Before starting a task in a repo, use memory-search to recall relevant durable knowledge (gotchas, conventions, prior decisions).

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)

Config Edits

All opencode config edits (opencode.json, AGENTS.md, skills/, agents/, commands/) go ONLY in workspace clone /root/workspace/opencode-config/, NEVER in ~/.config/opencode/ (bind-mount → edits bypass git → git pull conflicts on host). See skill configure-opencode for full sync procedure.

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.