diff --git a/docs/adr/ADR-001-workplan-convention.md b/docs/adr/ADR-001-workplan-convention.md
new file mode 100644
index 0000000..11333fa
--- /dev/null
+++ b/docs/adr/ADR-001-workplan-convention.md
@@ -0,0 +1,57 @@
+---
+id: ADR-001
+title: Workplan Convention
+status: accepted
+date: "2026-03-18"
+---
+
+# ADR-001 — Workplan Convention
+
+## Status
+
+Accepted
+
+## Context
+
+kaizen-agentic needs a way to track planned work that is version-controlled,
+visible to the state-hub, and authoritative when the two diverge.
+
+## Decision
+
+Work items originate as Markdown files in `workplans/` **before** being
+registered in the state-hub DB. The file is always authoritative; the DB is
+a read/query model derived from it.
+
+**File naming:** `workplans/kaizen-agentic-WP-NNNN-<slug>.md`
+**ID prefix:** `KAIZEN-WP`
+
+### Required YAML frontmatter
+
+```yaml
+---
+id: KAIZEN-WP-NNNN
+type: workplan
+title: "..."
+domain: custodian
+repo: kaizen-agentic
+status: active | completed | archived
+owner: kaizen-agentic
+topic_slug: custodian
+state_hub_workstream_id: <uuid>
+created: "YYYY-MM-DD"
+updated: "YYYY-MM-DD"
+---
+```
+
+### Task tracking
+
+Tasks use `- [ ]` / `- [x]` checkboxes with a `T##` code prefix. A
+`## State Hub Task IDs` table at the end of each workplan maps codes to
+DB UUIDs so status can be synced without a list_tasks lookup.
+
+## Consequences
+
+- File is the source of truth; DB drift is auto-fixable via
+  `check_repo_consistency(fix=True)`.
+- Tasks must be created in the file first, then registered in the hub.
+- C-12 warnings are expected when the DB host has not yet seen local changes.
diff --git a/docs/adr/ADR-002-project-memory-convention.md b/docs/adr/ADR-002-project-memory-convention.md
new file mode 100644
index 0000000..0e96712
--- /dev/null
+++ b/docs/adr/ADR-002-project-memory-convention.md
@@ -0,0 +1,119 @@
+---
+id: ADR-002
+title: Project Memory Convention
+status: accepted
+date: "2026-03-18"
+---
+
+# ADR-002 — Project Memory Convention
+
+## Status
+
+Accepted
+
+## Context
+
+kaizen-agentic agents are stateless by default — each session starts from
+scratch with no knowledge of what has been tried, what worked, or what the
+project's recurring patterns are. This makes agents less useful over time
+and forces the operator to re-supply context that the agent itself
+accumulated.
+
+## Decision
+
+Each agent deployed into a project may maintain a **project-scoped memory
+file**. Memory files are written at session close and read at session start.
+
+### File location
+
+```
+<project-root>/.kaizen/agents/<agent-name>/memory.md
+```
+
+The `.kaizen/` directory is the kaizen-agentic ecosystem's project-level
+state directory, analogous to `.claude/` for Claude Code.
+
+### Memory file structure
+
+```markdown
+---
+agent: <agent-name>
+project: <project-root or slug>
+last_updated: <ISO date>
+session_count: <n>
+---
+
+## Project Context
+<!-- What this agent knows about the project it works in -->
+
+## Accumulated Findings
+<!-- Patterns, recurring issues, key decisions encountered -->
+
+## What Worked
+<!-- Approaches that produced good results in this project -->
+
+## Watch Points
+<!-- Recurring risks, traps, or areas requiring extra care -->
+
+## Open Threads
+<!-- Things noticed but not yet acted on -->
+
+## Session Log
+<!-- One-line entry per session: date · summary · outcome -->
+```
+
+### Session-start protocol (all memory-enabled agents)
+
+1. Check for `.kaizen/agents/<name>/memory.md` in the project root.
+2. If present, read it before beginning work.
+3. Acknowledge the memory in the opening brief.
+
+### Session-close protocol (all memory-enabled agents)
+
+1. Update `## Accumulated Findings`, `## What Worked`, `## Watch Points`
+   as needed.
+2. Append one line to `## Session Log`.
+3. Bump `last_updated` and `session_count`.
+
+### Agent opt-out
+
+An agent may declare `memory: disabled` in its YAML frontmatter to opt out.
+Default is enabled. Stateless utility agents (e.g. `keepaTodofile`) should
+opt out.
+
+### CLI interface
+
+```
+kaizen-agentic memory show <agent>   # Print agent memory for current project
+kaizen-agentic memory init <agent>   # Scaffold empty memory file
+kaizen-agentic memory brief <agent>  # Run coach, print orientation for agent
+kaizen-agentic memory clear <agent>  # Wipe memory (with confirmation prompt)
+```
+
+`memory init` creates the `.kaizen/agents/<name>/memory.md` file with the
+standard structure and populates the frontmatter.
+
+### Coaching meta-agent
+
+A dedicated `agent-coach.md` (category: `meta`) reads across all
+`.kaizen/agents/*/memory.md` files in a project and:
+
+- Synthesises a cross-agent brief (shared patterns, cross-domain risks)
+- Produces a new-agent orientation targeted at a specific agent about to
+  be deployed for the first time
+- Maintains its own memory covering meta-level fleet observations
+
+`kaizen-agentic memory brief <agent>` invokes the coach to produce this
+orientation.
+
+## Consequences
+
+- Agents accumulate project-specific knowledge and arrive in later sessions
+  informed rather than blank.
+- The `.kaizen/` directory should be added to `.gitignore` by default;
+  teams may choose to commit it for shared context.
+- Memory files are human-readable and can be manually edited or reviewed.
+- The coach agent provides a single synthesised view across all agent
+  memories — reducing the operator's burden of re-supplying context.
+- Agents with `memory: disabled` remain fully stateless and require no
+  `.kaizen/` setup.
diff --git a/src/kaizen_agentic/cli.py b/src/kaizen_agentic/cli.py
index 7e91bc5..15835be 100644
--- a/src/kaizen_agentic/cli.py
+++ b/src/kaizen_agentic/cli.py
@@ -756,6 +756,140 @@ def remove(name: str, target: str):
         click.echo(f"❌ Extension not found: {name}")
 
 
+@cli.group()
+def memory():
+    """Manage project-scoped agent memory (.kaizen/agents/<name>/memory.md)."""
+    pass
+
+
+@memory.command("show")
+@click.argument("agent_name")
+@click.option("--target", "-t", default=".", help="Project root (default: current)")
+def memory_show(agent_name: str, target: str):
+    """Print agent memory for the current project."""
+    memory_path = _memory_path(target, agent_name)
+
+    if not memory_path.exists():
+        click.echo(f"No memory found for agent '{agent_name}'.")
+        click.echo(f"  Expected: {memory_path}")
+        click.echo(f"  Run: kaizen-agentic memory init {agent_name}")
+        return
+
+    click.echo(memory_path.read_text())
+
+
+@memory.command("init")
+@click.argument("agent_name")
+@click.option("--target", "-t", default=".", help="Project root (default: current)")
+def memory_init(agent_name: str, target: str):
+    """Scaffold an empty memory file for an agent."""
+    memory_path = _memory_path(target, agent_name)
+
+    if memory_path.exists():
+        click.echo(f"Memory file already exists: {memory_path}")
+        return
+
+    memory_path.parent.mkdir(parents=True, exist_ok=True)
+    project_name = Path(target).resolve().name
+
+    content = f"""---
+agent: {agent_name}
+project: {project_name}
+last_updated: {_today()}
+session_count: 0
+---
+
+## Project Context
+<!-- What this agent knows about the project it works in -->
+
+## Accumulated Findings
+<!-- Patterns, recurring issues, key decisions encountered -->
+
+## What Worked
+<!-- Approaches that produced good results in this project -->
+
+## Watch Points
+<!-- Recurring risks, traps, or areas requiring extra care -->
+
+## Open Threads
+<!-- Things noticed but not yet acted on -->
+
+## Session Log
+<!-- One-line entry per session: date · summary · outcome -->
+"""
+    memory_path.write_text(content)
+    click.echo(f"Initialized memory for '{agent_name}': {memory_path}")
+
+
+@memory.command("brief")
+@click.argument("agent_name")
+@click.option("--target", "-t", default=".", help="Project root (default: current)")
+def memory_brief(agent_name: str, target: str):
+    """Print a coach-synthesised orientation for an agent.
+
+    Reads this agent's memory and all other agent memories in the project.
+    Coach agent integration is pending (T13 — see KAIZEN-WP-0002).
+    Currently prints the agent's own memory as a starting orientation.
+    """
+    memory_path = _memory_path(target, agent_name)
+    kaizen_dir = Path(target).resolve() / ".kaizen" / "agents"
+
+    click.echo(f"=== Agent Brief: {agent_name} ===\n")
+
+    # Show own memory
+    if memory_path.exists():
+        click.echo(f"--- Memory: {agent_name} ---")
+        click.echo(memory_path.read_text())
+    else:
+        click.echo(f"No memory file found for '{agent_name}'. Run: memory init {agent_name}")
+
+    # List other agents with memory in this project
+    other_agents = []
+    if kaizen_dir.exists():
+        for agent_dir in kaizen_dir.iterdir():
+            if agent_dir.is_dir() and agent_dir.name != agent_name:
+                mf = agent_dir / "memory.md"
+                if mf.exists():
+                    other_agents.append(agent_dir.name)
+
+    if other_agents:
+        click.echo(f"\n--- Other agents with memory in this project: {', '.join(other_agents)} ---")
+        click.echo("(Coach synthesis not yet available — use 'memory show <agent>' to read each)")
+    else:
+        click.echo("\nNo other agent memories found in this project.")
+
+    click.echo("\nNote: Full coach synthesis will be available once agent-coach is implemented (KAIZEN-WP-0002 T12-T13).")
+
+
+@memory.command("clear")
+@click.argument("agent_name")
+@click.option("--target", "-t", default=".", help="Project root (default: current)")
+@click.confirmation_option(prompt="This will permanently delete the agent memory. Continue?")
+def memory_clear(agent_name: str, target: str):
+    """Wipe agent memory for the current project."""
+    memory_path = _memory_path(target, agent_name)
+
+    if not memory_path.exists():
+        click.echo(f"No memory found for agent '{agent_name}' — nothing to clear.")
+        return
+
+    memory_path.unlink()
+    click.echo(f"Cleared memory for '{agent_name}': {memory_path}")
+
+    # Remove empty parent directory
+    if not any(memory_path.parent.iterdir()):
+        memory_path.parent.rmdir()
+
+
+def _memory_path(target: str, agent_name: str) -> Path:
+    return Path(target).resolve() / ".kaizen" / "agents" / agent_name / "memory.md"
+
+
+def _today() -> str:
+    from datetime import date
+    return date.today().isoformat()
+
+
 def _get_registry() -> AgentRegistry:
     """Get the agent registry."""
     # Try to find agents directory
diff --git a/workplans/kaizen-agentic-WP-0002-agency-framework.md b/workplans/kaizen-agentic-WP-0002-agency-framework.md
index 410c823..6126531 100644
--- a/workplans/kaizen-agentic-WP-0002-agency-framework.md
+++ b/workplans/kaizen-agentic-WP-0002-agency-framework.md
@@ -138,8 +138,8 @@ kaizen-agentic memory clear <agent>     # Wipe memory (with confirmation)
 ### Tasks
 
 **Memory convention and tooling**
-- [ ] T07 — Write ADR: project memory convention (file location, structure, lifecycle)
-- [ ] T08 — Implement `memory` CLI command group (show, init, brief, clear)
+- [x] T07 — Write ADR: project memory convention (file location, structure, lifecycle)
+- [x] T08 — Implement `memory` CLI command group (show, init, brief, clear)
 - [ ] T09 — Add session-start and session-close protocol sections to agent template /
              contributor guide