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>
Sprint-based workflow (38 sprints) replaced by kanban + milestones.
Milestones are many-to-many with tickets and can block each other.
New: /whats-next skill (dependency-driven batch selection with Si
refinement review), /pr-process skill (renamed from pr-push, adds
review comment pickup), clerk agent + pre-push hook for D-record
consistency checks.
Deleted: sprint CLI, sprint-start/sprint-plan/sprint-status skills,
team-scoped file restrictions. Si rewritten as refinement manager.
All 19 agent briefings updated from stale PROJECT_STATE.md reference
to live ticket milestone queries.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The in-universe setting name is "the Settled Reach", not
"Commonwealth" (Hamilton's protected IP). Updated all 17 agent
description lines and intro paragraphs, plus file-specific
references in araminta, gore, ozzie, paula, and tiger.
Kept book references in miri.md (inspiration) and si.md (namesake).
Also updated pr-review and git-commit skill references.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Teams are server, client, copy, audio, visual, ci. Never use
"joint" — split cross-team work into per-team tickets with
explicit dependencies.
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