assembly-definitions
Assembly definition management — when to create asmdefs, reference rules, Editor/Runtime/Test separation, platform filters, compilation speed optimization.
Configures Claude Code's statusline to display Unity workflow state — current phase, active agent, files modified, and session duration.
$ npx -y skills add XeldarAlz/everything-claude-unity --skill hud-statusline --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/hud-statuslineContext preview
The summary Claude sees to decide when to auto-load this skill.
Configures Claude Code's statusline to display Unity workflow state — current phase, active agent, files modified, and session duration.
name: hud-statusline description: "Configures Claude Code's statusline to display Unity workflow state — current phase, active agent, files modified, and session duration." alwaysApply: false
Guidance for commands and agents to update Claude Code's statusline with real-time Unity workflow state.
The recommended statusline format for Unity workflows:
[Phase: Execute] [Agent: unity-coder] [Modified: 5 files] [12m]
Fields:
Statusline data comes from the hook state directory at `/tmp/unity-claude-hooks/`:
| File | Content | Updated By | |------|---------|-----------| | `session-edits.txt` | One file path per line (may have duplicates) | `track-edits.sh` | | `gateguard-reads.txt` | One file path per line | `track-reads.sh` | | `session-state.json` | Branch, phase, workflow context | `session-save.sh` | | `session-start-time` | Unix timestamp | `session-restore.sh` | | `session-cost.jsonl` | One JSON object per tool call | `cost-tracker.sh` |
EDIT_COUNT=0
if [ -f "/tmp/unity-claude-hooks/session-edits.txt" ]; then
EDIT_COUNT=$(sort -u "/tmp/unity-claude-hooks/session-edits.txt" | wc -l | tr -d ' ')
fiDURATION_MINS=0
if [ -f "/tmp/unity-claude-hooks/session-start-time" ]; then
START=$(cat "/tmp/unity-claude-hooks/session-start-time")
NOW=$(date +%s)
DURATION_MINS=$(( (NOW - START) / 60 ))
fiCommands with phase gates (like `/unity-workflow`) should update the statusline at each transition:
Phase 1: Clarify → statusline: [Phase: Clarify] Phase 2: Plan → statusline: [Phase: Plan] Phase 3: Execute → statusline: [Phase: Execute] [Agent: unity-coder] Phase 4: Verify → statusline: [Phase: Verify] [Agent: unity-verifier] Done → statusline: [Phase: Done] [Modified: N files] [Xm]
When a command spawns a sub-agent, the statusline should reflect which agent is active. The agent field updates when:
During `/unity-ralph`, the statusline should show iteration progress:
[Ralph: 3/10] [Agent: unity-verifier] [Fixed: 5] [12m]
During `/unity-team`, the statusline should show parallel agent status:
[Team: build] [Agents: 3 running] [Modified: 8 files] [5m]
If the cost tracker is active (strict profile), the statusline can optionally show token usage:
[Phase: Execute] [Modified: 5 files] [12m] [Calls: 47]
Read from `session-cost.jsonl`:
CALL_COUNT=0
if [ -f "/tmp/unity-claude-hooks/session-cost.jsonl" ]; then
CALL_COUNT=$(wc -l < "/tmp/unity-claude-hooks/session-cost.jsonl" | tr -d ' ')
fiThe ultimate Claude Code toolkit for Unity game development. A production-ready, plug-and-play system that gives Claude Code deep Unity expertise — from writing performant C# to building scenes, profiling performance, and triggering iOS/Android builds — all
Assembly definition management — when to create asmdefs, reference rules, Editor/Runtime/Test separation, platform filters, compilation speed optimization.
Structured commit trailers — adds Constraint, Rejected, Scope-risk, and Not-tested metadata to commit messages. Captures architectural decisions and known gaps…
Ambiguity gating — detects vague feature requests and forces structured requirements gathering with scoring across scope, platform, performance, integration,…
Event system patterns — C# events, UnityEvent, SO event channels, static EventBus. When to use each, zero-allocation patterns, memory leak prevention.
Post-debugging knowledge extraction — captures non-obvious, codebase-specific learnings that pass quality gates. Invoke after resolving tricky bugs or…
Heuristics for choosing the right model tier (haiku/sonnet/opus) when delegating to agents. Loaded by orchestrating commands to inform agent selection.