extra pt2

.config/opencode/.memory/knowledge/conventions.md

@@ -0,0 +1,36 @@
+# Conventions
+
+## File Organization
+
+```
+~/.config/opencode/
+├── opencode.jsonc          # Main config (default agent, plugins, permissions)
+├── AGENTS.md               # Cross-tool instructions (single source of truth)
+├── CLAUDE.md -> AGENTS.md  # Symlink for Claude
+├── .cursorrules -> AGENTS.md  # Symlink for Cursor
+├── agents/                 # Agent definitions
+│   ├── lead.md
+│   ├── coder.md
+│   ├── reviewer.md
+│   └── ...
+├── skills/                 # Reusable skill modules
+│   └── doc-coverage/
+└── .memory/               # Persistent memory
+```
+
+## Naming Conventions
+
+- Agent files: `{role}.md` (e.g., `coder.md`, `reviewer.md`)
+- Plan files: `{feature}.md` (e.g., `memory-restructure.md`)
+- Research files: `{topic}.md` (e.g., `micode-memory-system.md`)
+- Gate files: `{feature}.md` (e.g., `auth-flow.md`)
+
+## Memory Structure
+
+See [Memory Structure](../manifest.yaml) for the canonical structure.
+
+## Cross-Tool Instructions
+
+- `AGENTS.md` is the single source of truth
+- All other instruction files are symlinks to it
+- Never edit symlinked files directly

.config/opencode/.memory/knowledge/domain/concepts.md

@@ -0,0 +1,35 @@
+# Domain Concepts
+
+## Agent Roles
+
+| Role | Responsibility |
+|------|----------------|
+| Lead | Primary orchestrator — decomposes work, delegates, synthesizes |
+| Coder | Implementation-focused coding |
+| Reviewer | Code quality, correctness, security review |
+| Tester | Functional and adversarial testing |
+| Explorer | Fast codebase mapping and discovery |
+| Researcher | Deep technical investigation |
+| Librarian | Documentation coverage and accuracy |
+| Critic | Pre-implementation gate and blocker resolution |
+| SME | Domain-specific consultation |
+| Designer | UI/UX interaction and visual guidance |
+
+## Memory Categories
+
+| Category | Purpose | Location |
+|----------|---------|----------|
+| Knowledge | Persistent project understanding | `.memory/knowledge/` |
+| Decisions | Architecture Decision Records | `.memory/decisions.md` |
+| Plans | Active implementation plans | `.memory/plans/` |
+| Research | Technical investigations | `.memory/research/` |
+| Gates | Quality gate records | `.memory/gates/` |
+| Sessions | Session continuity | `.memory/sessions/` |
+
+## Quality Pipeline Flow
+
+Standard flow: `explorer/researcher → coder → reviewer → tester → librarian`
+
+Exceptions:
+- Tier 3: skips tester
+- Tier 1: adds security reviewer and adversarial tester

.config/opencode/.memory/knowledge/overview.md

@@ -0,0 +1,40 @@
+# 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:** `AGENTS.md` is the single real instruction file; `CLAUDE.md`, `.cursorrules`, and `.github/copilot-instructions.md` are symlinks to it.
+
+## Agent Architecture
+
+10 agents with distinct roles, models, and permission profiles. See [Agent Roster in AGENTS.md](../../AGENTS.md#agent-roster) 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](../decisions.md#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):
+
+1. Each agent's instructions explicitly state: "`.memory/*` writes are allowed for [specific duty]; code/source edits remain read-only."
+2. Each agent's instructions list tool restrictions (e.g., "Disallowed: non-memory file edits").
+3. 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 (`AGENTS.md`) plus symlink correctness for `CLAUDE.md`, `.cursorrules`, and `.github/copilot-instructions.md`, 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](../../AGENTS.md#cross-tool-instruction-files) and [Doc coverage checklist section 3](../skills/doc-coverage/SKILL.md#3-instruction-file).

.config/opencode/.memory/knowledge/patterns/error-handling.md

@@ -0,0 +1,21 @@
+# Error Handling Patterns
+
+## Agent-Level Error Handling
+
+Agents follow the retry circuit breaker pattern defined in `agents/lead.md`:
+
+- After 3 coder rejections on the same task: revisit design, simplify, or consult SME
+- After 5 total failures: escalate to user (Tier-3 escalation)
+
+## Memory Write Errors
+
+Agents with memory-only edit access should:
+1. Write to `.memory/*` files for their recording duties
+2. If write fails, report to lead for escalation
+3. Never attempt to modify non-memory files as a workaround
+
+## Quality Gate Failures
+
+- Reviewer `CHANGES-REQUESTED` is a hard block — do not advance to tester
+- Reviewer `REJECTED` requires redesign — do not retry same approach
+- Tester `PARTIAL` is not a pass — either fix blocker or escalate to user

.config/opencode/.memory/knowledge/patterns/logging.md

@@ -0,0 +1,27 @@
+# Logging Patterns
+
+## Agent Output Standards
+
+Subagents must return actionable results, not status recaps:
+
+| Agent | Expected Output |
+|-------|-----------------|
+| Explorer | File maps, edit points, dependency chains |
+| Researcher | Specific findings, code patterns, API details |
+| Tester | Test results with pass/fail counts and specific failures |
+| Reviewer | Structured verdict with findings and resolution status |
+
+## Recording Discipline
+
+Memory files preserve *knowledge*, not *activity logs*:
+
+- ✅ Record: outcomes, decisions, discoveries, patterns
+- ❌ Don't record: phase transitions, status changes, ceremony checkpoints
+
+## Verdict Tracking
+
+All reviewer/tester findings must be tracked to resolution:
+
+- Status flow: `OPEN → ASSIGNED → RESOLVED | WONTFIX`
+- Findings must not be silently dropped
+- Include unresolved findings in coder re-dispatch

.config/opencode/.memory/knowledge/patterns/testing.md

@@ -0,0 +1,25 @@
+# Testing Patterns
+
+## Verification Tiers
+
+| Tier | Scope | Pipeline |
+|------|-------|----------|
+| Tier 1 | New features, security-sensitive, multi-file refactors | coder → reviewer:correctness → reviewer:security → tester:standard → tester:adversarial |
+| Tier 2 | Moderate changes, UI updates, bug fixes | coder → reviewer:correctness → tester:standard |
+| Tier 3 | Single-file fixes, config tweaks, copy changes | coder → reviewer:correctness |
+
+## Functional Verification Requirements
+
+Static analysis is NOT verification. Every feature must be functionally verified:
+
+- **API endpoints**: Real HTTP requests with response verification
+- **Frontend**: Browser-based or test-suite verification
+- **Full-stack**: End-to-end UI → API → DB → response cycle
+- **Bug fixes**: Reproduce bug, verify it no longer occurs
+
+## What Does NOT Count as Verification
+
+- ❌ Type checks (`tsc`, `bun run check`)
+- ❌ Linting (`eslint`, `ruff`)
+- ❌ Build succeeding
+- ❌ Reading code and concluding "this looks correct"

.config/opencode/.memory/knowledge/tech-stack.md

@@ -0,0 +1,22 @@
+# Tech Stack
+
+## Core Technologies
+
+| Component | Technology | Notes |
+|-----------|------------|-------|
+| Runtime | OpenCode CLI | Agentic coding tool |
+| Config format | JSONC | `opencode.jsonc` with comments |
+| Agent definitions | Markdown + YAML frontmatter | `agents/*.md` |
+| Memory system | Markdown + YAML | `.memory/` directory |
+
+## MCP Servers
+
+| Server | Purpose | Endpoint |
+|--------|---------|----------|
+| 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 | Local |
+
+## Model Assignments
+
+See [Agent Roster](../../AGENTS.md#agent-roster) for model assignments per agent role.