- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add athola/claude-night-market --skill escalation-governance -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add athola/claude-night-market --skill escalation-governance -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add athola/claude-night-market --skill escalation-governance -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add athola/claude-night-market --skill escalation-governance -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/athola/claude-night-market/tree/HEAD/plugins/abstract/skills/escalation-governanceFrom the publisher
Model 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:
Illegitimate escalation triggers:
Before escalating, answer these questions:
If knowledge gap: Gather more information, don't escalate.
Two coexisting implementations of one concern make a task look harder
than it is. That is a knowledge gap: count them with a reference search
and read both before escalating (docs/knowledge-corpus/decoherence.md,
which calls them models of a concern).
If not investigated: Complete investigation first.
If decomposable: Break down, don't escalate.
If not proportional: Don't escalate.
When escalation IS justified:
Escalation needs a reason tied to the task. These common ones fail the four steps above, and the constraint behind each says why:
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.
MCP Tool Search (Claude Code 2.1.7+): Haiku models do not support MCP tool search. If a workflow uses many MCP tools (descriptions exceeding 10% of context), those tools load upfront on haiku instead of being deferred. This can consume significant context. Consider escalating to sonnet for MCP-heavy workflows or ensure haiku agents use only native tools (Read, Write, Bash, etc.).
Claude.ai MCP Connectors (Claude Code 2.1.46+): Users with claude.ai connectors configured may have additional MCP tools auto-loaded, increasing the total tool description footprint. This makes it more likely that haiku agents will exceed the 10% tool search threshold. When escalation decisions involve MCP-heavy workflows, factor in claude.ai connector tool count via /mcp.
Effort Controls as Escalation Alternative (Opus 4.6 / Claude Code 2.1.32+): Opus 4.6 introduces adaptive thinking with effort levels (low, medium, high). The max level was removed in 2.1.72 for Opus 4.6, and high became the ceiling on that model. Claude Code 2.1.111 reintroduced max and added xhigh (between high and max) for Opus 4.7 only; on other models xhigh falls back to high. Symbols: ○ (low) ◐ (medium) ● (high) ◉ (xhigh) ★ (max). Use /effort (interactive slider since 2.1.111) or /effort auto to reset. Before escalating between models, consider whether adjusting effort on the current model would suffice:
Default effort change (2.1.68+): Opus 4.6 now
defaults to medium effort for Max and Team
subscribers. Use /model to change effort level, or
type "ultrathink" in your prompt to enable high effort
for the next turn.
Opus 4/4.1 removed (2.1.68+): Opus 4 and 4.1 are
no longer available on the first-party API. Users with
these models pinned are automatically migrated to
Opus 4.6. No action needed for agents using model
frontmatter, as the migration is transparent.
Sonnet 4.5 → 4.6 migration (2.1.69+): Sonnet 4.5
users on Pro/Max/Team Premium are automatically migrated
to Sonnet 4.6. Agent model frontmatter referencing
Sonnet resolves transparently. The --model flags for
claude-opus-4-0 and claude-opus-4-1 now correctly
resolve to Opus 4.6 instead of deprecated versions.
Effort parameter fix (2.1.70+): Fixed API 400 error
This model does not support the effort parameter when
using custom Bedrock inference profiles or non-standard
Claude model identifiers. Effort controls now work
reliably across all deployment configurations.
Default Opus 4.6 on providers (2.1.73+): Bedrock,
Vertex, and Microsoft Foundry now default to Opus 4.6
(was Opus 4.1). Subagent model: opus/sonnet/haiku
aliases now resolve to the current version on all
providers. Previously they were silently downgraded to
older versions (e.g., Opus 4.1 instead of 4.6). This
fix means agent dispatch workflows on third-party
providers now match first-party API behavior.
modelOverrides setting (2.1.73+): Maps model
picker entries to provider-specific IDs (Bedrock
inference profile ARNs, Vertex version names, Foundry
deployment names). Use when routing model selections to
specific inference profiles. See the model optimization
guide for configuration details.
/output-style deprecated (2.1.73+): Use /config
instead. Output style is now fixed at session start for
better prompt caching.
Full model IDs in agent frontmatter (2.1.74+): Agent
model: fields now accept full model IDs (e.g.,
claude-opus-4-6) in addition to aliases (opus,
sonnet, haiku). Previously, full IDs were silently
ignored. Agents now accept the same values as --model.
Effort controls do NOT replace the escalation governance framework: they provide an additional axis. The Iron Law still applies: investigate before changing either model or effort level.
Assess whether to escalate models. Use when evaluating reasoning depth.
---name: escalation-governancedescription: Assess whether to escalate models. Use when evaluating reasoning depth.---# plugins/abstract/skills/escalation-governance/SKILL.mdFAQ
Download plugins/abstract/skills/escalation-governance/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/athola/claude-night-market.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.