dotfiles/.config/opencode/.memory/knowledge.md at 20b7ef0ea6bebcf0ae8eaef98904724c23c9334a

Files

alex e9074646b7 feat: adopt symlink approach for cross-tool instruction files

Replace 4 separate instruction files with 1 real file + symlinks:
- .github/copilot-instructions.md is the canonical instruction file
- CLAUDE.md and .cursorrules are symlinks to it
- AGENTS.md stays as global config (not a project instruction file)

This eliminates all sync/merge logic - changes propagate automatically.

Changes:
- AGENTS.md: rewrite Cross-Tool Instruction Files section for symlink convention
- librarian.md: simplify to maintain single instruction file + verify symlinks
- lead.md: simplify PHASE-WRAP and Documentation Completion Gate
- commands (init, bootstrap-memory, save-memory): update for symlink model
- doc-coverage skill: verify symlinks exist and point correctly

2026-03-08 23:48:42 +00:00

3.1 KiB

Raw Blame History

Project Overview

This is the OpenCode agentic configuration for a multi-agent coding workflow. It defines agent roles, permissions, quality pipelines, and project memory conventions used across all projects that load this config.

Config root: ~/.config/opencode/
Config file: opencode.jsonc — defines default agent, plugins, global permissions, and MCP servers.
Agent definitions: agents/*.md — one file per agent with YAML frontmatter (model, permissions, temperature) and markdown instructions.
Memory system: .memory/ — persistent project knowledge, decisions, plans, and research in markdown.
Cross-tool instruction files: .github/copilot-instructions.md is the single real instruction file; AGENTS.md, CLAUDE.md, and .cursorrules should be symlinks to it.

Agent Architecture

10 agents with distinct roles, models, and permission profiles. See Agent Roster in AGENTS.md for the full table.

Permission Model

Full edit access: lead, coder, librarian.
Memory-only edit access: reviewer, tester, explorer, researcher, critic, sme, designer — these agents have permission.edit: allow but are instructed to keep code/source edits read-only. Their edit permission exists solely to support .memory/* writes for recording duties (verdicts, discoveries, research, guidance, design decisions).
No edit access: none (all agents can write .memory/*).

See Decision: Agent Memory Write Access for rationale and guardrails.

Memory Write Guardrails

Agents with memory-only edit access are constrained by instruction-level guardrails (not path-scoped config, which OpenCode does not support):

Each agent's instructions explicitly state: ".memory/* writes are allowed for [specific duty]; code/source edits remain read-only."
Each agent's instructions list tool restrictions (e.g., "Disallowed: non-memory file edits").
The permission.edit: allow fallback is necessary because OpenCode's permission.edit does not support path-scoped allow/deny syntax.

Quality Pipeline

Tiered pipeline (Tier 1/2/3) defined in agents/lead.md. Standard flow: explorer/researcher → coder → reviewer → tester → librarian.

Documentation Skill Conventions

skills/doc-coverage/SKILL.md section ### 3. Instruction File validates one canonical instruction file (.github/copilot-instructions.md) plus symlink correctness for AGENTS.md, CLAUDE.md, and .cursorrules, rather than treating all four as independently edited files.
The checklist explicitly flags duplication of .memory/ tracking content (plans/research) inside instruction files as an anti-pattern.

See Cross-Tool Instruction Files and Doc coverage checklist section 3.

MCP Servers

Context7: Remote documentation lookup (https://mcp.context7.com/mcp)
GitHub Grep: Remote code search across public repos (https://mcp.grep.app)
Playwright: Local headless Chromium for UI testing

3.1 KiB Raw Blame History