Phase 1 follow-up: update the active instruction layer (CLAUDE.md, project
structure rule, DECISIONS.md redirect, agent personalities, skill docs) to
reference governance/{decisions,questions,rejected}/<domain>.md instead of the
retired flat decisions/*.md layout.
Path references only — command-surface references (tooling/db/decision*,
decisions-sync, Makefile targets, clerk) are repointed to the pql CLI in the
Phase 4 consumer cutover. Historical archives (docs/sprints, docs/discussions,
docs/workshops) keep their point-in-time decisions/ paths; the separate
whatsinagame/ template distribution is untouched. Agent-memory is gitignored
and out of scope.
The agent/skill repath was applied by tooling/pql-migrate/repath_references.py
(ordered, meaning-preserving replacements; bare-dir rule uses a negative
lookbehind so it can't corrupt a freshly-created governance/decisions/ path),
committed for provenance. CLAUDE.md, project-structure.md, and DECISIONS.md
were hand-edited (structural tree/table changes).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Only Qatux (the librarian — cross-session recall is its job) keeps
project memory. Removed memory: project from the 20 ephemeral
implementer/reviewer/design agents that are spawned per-task and die:
they have no curation discipline and already use decisions/ + briefings/
as shared memory, so an uncurated per-agent store only invited rot.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Custom subagent types used as agent-team teammates in tmux pane mode only
receive their definition's restricted tools list — the coordination tools
are not injected (confirmed on Claude Code 2.1.148). Without SendMessage a
teammate can't message the lead and can't return a shutdown_response, so it
orphans its pane.
Add SendMessage, TaskList, TaskUpdate, and TaskGet to all 21 agents so they
work as full teammates. TaskCreate is intentionally omitted: task creation
stays centralized with the team lead.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- CLAUDE.md: add "Pair session" as formal work mode alongside sprint mode
- Scrap NPC ambient systems (R-012): D-078 marked superseded, content
pattern note scrapped, overheard conversation system will be rebuilt
from scratch after a walkable environment exists
- Agent profiles: remove NPC-drift references from Paula, Dudley, Miri;
add cascade discipline to Miri's role
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Agent personality files and skill definitions updated to reference decisions/
domain files instead of monolithic DECISIONS.md.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Miri now flags concepts that drift too close to specific franchises
(Hamilton, Banks, Reynolds, Simmons, Morgan) and proposes original
alternatives. "Inspired by" means structural dynamics, not surface
details.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Pivot to original IP means Miri no longer guards Hamilton canon.
New role: designs and maintains the original SF setting, ensures
internal consistency, grounds features in worldbuilding. Updated
agent file, agents README, and team roster.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Set up Commonwealth game project with complete agent team (18 agents),
discussion archives (12 rounds), briefing system, ticketing database,
Qdrant document search, and skill definitions. Establishes the
documentation and tooling foundation for engine selection and
implementation phases.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
jpmschweitzerandClaude Opus 4.8