docs(core): refine project intelligence system and deprecate legacy context (#93 )

* feat(context): Add project intelligence system

- Add project-intelligence.md standard (what & why)
- Add project-intelligence-management.md guide (how to manage)
- Add project-intelligence/ folder with 6 context files:
  - navigation.md (quick overview & routes)
  - business-domain.md (business context, users, value)
  - technical-domain.md (stack, architecture, decisions)
  - business-tech-bridge.md (business → technical mapping)
  - decisions-log.md (decision history with context)
  - living-notes.md (active issues, debt, questions)
- Update standards navigation with new entries
- Register all new contexts in registry.json

This enables projects to document and maintain business + technical
context for quick onboarding and lasting project understanding.

* fix(registry): Add project-intelligence to profiles

- Add context:project-intelligence/* to developer, business, full, and advanced profiles
- Ensures project intelligence contexts are included when these profiles are selected

This complements commit c731328 which added the context entries.

* docs(core): refine project intelligence system and deprecate legacy context

2026-01-13 11:25:18 +00:00

2.6 KiB

Raw Blame History

⚠️ DEPRECATED: OpenCode Agent System Project Context

⛔ This file is deprecated. See project-intelligence/technical-domain.md for the current technical domain documentation.

Technology Stack

Primary Language: TypeScript Runtime: Node.js/Bun Package Manager: npm/pnpm/yarn Build Tools: TypeScript Compiler (tsc) Testing: Jest/Vitest (if configured) Linting: ESLint (if configured)

Project Structure

.opencode/
├── agent/           # AI agents for specific tasks
│   ├── subagents/   # Specialized subagents
│   └── *.md         # Primary agents
├── command/         # Slash commands
├── context/         # Knowledge base for agents
└── plugin/          # Extensions and integrations

tasks/               # Task management files

Core Patterns

Agent Structure Pattern

---
description: "What this agent does"
mode: primary|subagent
tools: [read, edit, bash, etc.]
permissions: [security restrictions]
---

# Agent Name

[Direct instructions for behavior]

**EXECUTE** this [process type] for every [task type]:

**1. [ACTION]** the [subject]:
- [Specific instruction 1]
- [Specific instruction 2]

**RULES:**
- **ALWAYS** [critical requirement]
- **NEVER** [forbidden action]

Command Structure Pattern

---
name: command-name
agent: target-agent
---

You are [doing specific task].

**Request:** $ARGUMENTS

**Context Loaded:**
@.opencode/context/core/essential-patterns.md
@[additional context files]

Execute [task] now.

Context Loading Rules

Commands load context immediately using @ references
Agents can look up additional context deterministically
Maximum 4 context files per command (250-450 lines total)
Keep context files focused (50-150 lines each)

Security Guidelines

Agents have restricted permissions by default
Sensitive operations require explicit approval
No direct file system modifications without validation
Build commands limited to safe operations

Development Workflow

Planning: Create detailed task plans for complex work
Implementation: Execute one step at a time with validation
Review: Code review and security checks
Testing: Automated testing and build validation
Documentation: Update docs and context files

Quality Gates

TypeScript compilation passes
Code review completed
Build process succeeds
Tests pass (if available)
Documentation updated

2.6 KiB Raw Blame History