mirror of https://github.com/Donchitos/Claude-Code-Game-Studios.git synced 2026-10-16 01:37:05 +00:00

Files

T

DonchitosandClaude Opus 5.5 be8993bbc5 Release 1.1.3 — long skills keep their later steps

Fix release for 1.1.2: the 14 longest skills keep their later phases
after a compaction, a question nobody answered is never taken as an
answer, settings read the same from a subfolder, the commit check works
for a project in a subfolder of a larger repository, every skill opens
with a title, and the shipped allow rules no longer approve deleting a
branch or writing files without asking. Details in CHANGELOG.md; upgrade
steps in UPGRADING.md (v1.1.2 → v1.1.3).

Refs #83
Refs #133

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0185en4t76fPn7315q4c3nko

2026-10-08 17:52:48 +11:00

2.7 KiB

Raw Blame History

Agent Coordination Rules

Vertical Delegation: Leadership agents delegate to department leads, who delegate to specialists. Never skip a tier for complex decisions.
Horizontal Consultation: Agents at the same tier may consult each other but must not make binding decisions outside their domain.
Conflict Resolution: When two agents disagree, escalate to the shared parent. If no shared parent, escalate to creative-director for design conflicts or technical-director for technical conflicts.
Change Propagation: When a design change affects multiple domains, the producer agent coordinates the propagation.
No Unilateral Cross-Domain Changes: An agent must never modify files outside its designated directories without explicit delegation.

Model Tier Assignment

Read .claude/docs/model-tiers.md on demand. It carries the tier table, the per-skill assignments and the authoring rule.

Key point: whether a skill's model: is used depends on how the skill starts. Typed as /skill-name: yes, except a haiku pin in auto mode. Started by Claude through the Skill tool: no. Never tell a user a haiku skill saves money; an opus skill typed in a Sonnet session costs more. The agent-side model: is a different mechanism, and is applied.

Subagents vs Agent Teams

This project uses two distinct multi-agent patterns:

Subagents (current, always active)

Spawned via the Agent tool within a single Claude Code session (renamed from Task in Claude Code 2.1.63; Task still works as an alias). Used by all team-* skills and orchestration skills. Subagents share the session's permission context, run sequentially or in parallel within the session, and return results to the parent.

When to spawn in parallel: If two subagents' inputs are independent (neither needs the other's output to begin), spawn both Agent calls simultaneously rather than waiting. Example: /review-all-gdds Phase 2 (consistency) and Phase 3 (design theory) are independent — spawn both at the same time. Phase 1 loads the GDDs and both depend on it, so it is the one phase here that must NOT be parallelised.

Agent Teams (experimental — opt-in)

Multiple independent Claude Code sessions coordinated via a shared task list. Opt-in only — read .claude/docs/agent-teams.md on demand before proposing one.

Parallel Task Protocol

When an orchestration skill spawns multiple independent agents:

Issue all independent Agent calls before waiting for any result
Collect all results before proceeding to dependent phases
If any agent is BLOCKED, surface it immediately — do not silently skip
Always produce a partial report if some agents complete and others block

2.7 KiB Raw Blame History