Enhance autopilot documentation and workflows: Add assumptions regarding single project per workspace, update notification sound references, and introduce context budget heuristics for managing session limits. Revise various skill documents to reflect changes in task management, including ticketing and testing processes, ensuring clarity and consistency across the system.

.cursor/skills/autopilot/protocols.md

@@ -46,7 +46,7 @@ Rules:
 2. Always include a recommendation with a brief justification
 3. Keep option descriptions to one line each
 4. If only 2 options make sense, use A/B only — do not pad with filler options
-5. Play the notification sound (per `human-input-sound.mdc`) before presenting the choice
+5. Play the notification sound (per `human-attention-sound.mdc`) before presenting the choice
 6. Record every user decision in the state file's `Key Decisions` section
 7. After the user picks, proceed immediately — no follow-up confirmation unless the choice was destructive
 
@@ -154,7 +154,7 @@ After 3 failed auto-retries of the same skill, the failure is likely not user-re
    - Set `status: failed` in `Current Step`
    - Set `retry_count: 3`
    - Add a blocker entry describing the repeated failure
-2. Play notification sound (per `human-input-sound.mdc`)
+2. Play notification sound (per `human-attention-sound.mdc`)
 3. Present using Choose format:
 
 ```
@@ -251,6 +251,32 @@ When a skill needs to read large files (e.g., full solution.md, architecture.md)
 - Use search tools (Grep, SemanticSearch) to find specific sections rather than reading entire files
 - Summarize key decisions from prior steps in the state file so they don't need to be re-read
 
+### Context Budget Heuristic
+
+Agents cannot programmatically query context window usage. Use these heuristics to avoid degradation:
+
+| Zone | Indicators | Action |
+|------|-----------|--------|
+| **Safe** | State file + SKILL.md + 2–3 focused artifacts loaded | Continue normally |
+| **Caution** | 5+ artifacts loaded, or 3+ large files (architecture, solution, discovery), or conversation has 20+ tool calls | Complete current sub-step, then suggest session break |
+| **Danger** | Repeated truncation in tool output, tool calls failing unexpectedly, responses becoming shallow or repetitive | Save immediately, update state file, force session boundary |
+
+**Skill-specific guidelines**:
+
+| Skill | Recommended session breaks |
+|-------|---------------------------|
+| **document** | After every ~5 modules in Step 1; between Step 4 (Verification) and Step 5 (Solution Extraction) |
+| **implement** | Each batch is a natural checkpoint; if more than 2 batches completed in one session, suggest break |
+| **plan** | Between Step 5 (Test Specifications) and Step 6 (Epics) for projects with many components |
+| **research** | Between Mode A rounds; between Mode A and Mode B |
+
+**How to detect caution/danger zone without API**:
+
+1. Count tool calls made so far — if approaching 20+, context is likely filling up
+2. If reading a file returns truncated content, context is under pressure
+3. If the agent starts producing shorter or less detailed responses than earlier in the conversation, context quality is degrading
+4. When in doubt, save and suggest a new conversation — re-entry is cheap thanks to the state file
+
 ## Rollback Protocol
 
 ### Implementation Steps (git-based)