Guide to deciding whether to escalate from a lower model (haiku/sonnet) to a higher model (sonnet/opus). Triggers: model escalation, haiku to sonnet, sonnet to opus, reasoning depth, task complexity, model selection, capability trade-off Use when: evaluating whether to escalate models, facing genuine complexity requiring deeper reasoning, novel patterns with no existing solutions, high-stakes decisions requiring capability investment DO NOT use when: thrashing without investigation - investigate root cause first. DO NOT use when: time pressure alone - urgency doesn't change task complexity. DO NOT use when: "just to be safe" - assess actual complexity instead. NEVER escalate without investigation first. This is the Iron Law.
/plugin marketplace add athola/claude-night-market/plugin install abstract@claude-night-marketThis skill inherits all available tools. When active, it can use any tool Claude has access to.
test-authority.mdtest-convenience.mdtest-false-complexity.mdtest-thrashing.mdModel escalation (haiku→sonnet→opus) trades speed/cost for reasoning capability. This trade-off must be justified.
Core principle: Escalation is for tasks that genuinely require deeper reasoning, not for "maybe a smarter model will figure it out."
NO ESCALATION WITHOUT INVESTIGATION FIRST
Escalation is never a shortcut. If you haven't understood why the current model is insufficient, escalation is premature.
Legitimate escalation triggers:
| Trigger | Description | Example |
|---|---|---|
| Genuine complexity | Task inherently requires nuanced judgment | Security policy trade-offs |
| Reasoning depth | Multiple inference steps with uncertainty | Architecture decisions |
| Novel patterns | No existing patterns apply | First-of-kind implementation |
| High stakes | Error cost justifies capability investment | Production deployment |
| Ambiguity resolution | Multiple valid interpretations need weighing | Spec clarification |
Illegitimate escalation triggers:
| Anti-Pattern | Why It's Wrong | What to Do Instead |
|---|---|---|
| "Maybe smarter model will figure it out" | This is thrashing | Investigate root cause |
| Multiple failed attempts | Suggests wrong approach, not insufficient capability | Question your assumptions |
| Time pressure | Urgency doesn't change task complexity | Systematic investigation is faster |
| Uncertainty without investigation | You haven't tried to understand yet | Gather evidence first |
| "Just to be safe" | False safety - wastes resources | Assess actual complexity |
Before escalating, answer these questions:
If knowledge gap: Gather more information, don't escalate.
If not investigated: Complete investigation first.
If decomposable: Break down, don't escalate.
If not proportional: Don't escalate.
When escalation IS justified:
| Excuse | Reality |
|---|---|
| "This is complex" | Complex for whom? Have you tried? |
| "Better safe than sorry" | Safety theater wastes resources |
| "I tried and failed" | How many times? Did you investigate why? |
| "The user expects quality" | Quality comes from process, not model size |
| "Just this once" | Exceptions become habits |
| "Time is money" | Systematic approach is faster than thrashing |
Agents can declare escalation hints in frontmatter:
model: haiku
escalation:
to: sonnet # Suggested escalation target
hints: # Advisory triggers (orchestrator may override)
- security_sensitive # Touches auth, secrets, permissions
- ambiguous_input # Multiple valid interpretations
- novel_pattern # No existing patterns apply
- high_stakes # Error would be costly
Key points:
The orchestrator (typically Opus) makes final escalation decisions:
Can follow hints: When hint matches observed conditions Can override to escalate: When context demands it (even without hints) Can override to stay: When task is simpler than hints suggest Can escalate beyond hint: Go to opus even if hint says sonnet
The orchestrator's judgment, informed by conversation context, supersedes static hints.
If you catch yourself thinking:
ALL of these mean: STOP. Investigate first.
Agent starts task at assigned model
├── Task succeeds → Complete
└── Task struggles →
├── Investigate systematically
│ ├── Root cause found → Fix at current model
│ └── Genuine capability gap → Escalate with justification
└── Don't investigate → WRONG PATH
└── "Maybe escalate?" → NO. Investigate first.
| Situation | Action |
|---|---|
| Task inherently requires nuanced reasoning | Escalate |
| Agent uncertain but hasn't investigated | Investigate first |
| Multiple attempts failed | Question approach, not model |
| Security/high-stakes decision | Escalate |
| "Maybe smarter model knows" | Never escalate on this basis |
| Hint fires, task is actually simple | Override, stay at current model |
| No hint fires, task is actually complex | Override, escalate |
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.