宜博 / lemongraph

Real production gap found while resuming stuck self-hosting tasks:
.claude/agents/planner_reviewer.md was never deployed after Phase 1 (Org
Graph unification, commit ea19c7d) added the planner_reviewer role --
role.json/SOUL.md/AGENTS.md all existed, but nobody re-ran
agent_profile.deploy_agent_definitions() against this live checkout after
adding the role, so every task reaching the planner_reviewer review stage
failed immediately with "claude --agent 'planner_reviewer' not found" and
landed on blocked_pending_human/execution_error. This has silently been
blocking every task since Phase 1 shipped.

Re-running deploy_agent_definitions() also caught coder.md/validator.md
drifting out of sync with their role.json skills lists (missing
design-dynamic-work-graph, work-graph-node-review, skill-defect-remediation,
unknown-scope-defect-sweep -- accumulated from several sessions' worth of
role.json edits that never got redeployed). planner.md was already in sync.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

U-004 migrated the Hermes personas into agents/{planner,coder,validator}/SOUL.md
(the canonical source) but nothing had ever actually deployed the compiled
.claude/agents/*.md into graphlemon's own repo -- every real test throughout
PH1-PH4 ran against throwaway target-project clones that got this step via
project_scaffold, never against graphlemon self-targeting itself. The real
U-042 self-hosting attempt surfaced this immediately: `claude --agent planner`
failed outright with "--agent 'planner' not found". Deployed via
agent_profile.deploy_agent_definitions() and committed -- self-target worktree
isolation only sees committed content, so this has to be tracked, not just
written to disk, for any future self-target task to find its own persona.

Also commits the real agent-memory files a genuine self-target run generated
(architecture doc §8 decision 1: memory must be git-traceable) and gitignores
.claude/workflows/ (one-shot, uniquely-named dynamic-workflow scripts written
per Work Node call -- pure runtime clutter, never reused, not source content).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>