Effort Calibrator
Pick the right Fable 5 effort level per workload — stop overpaying for xhigh.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/effort-calibrator-kpab/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Choose and tune the effort setting for Claude Fable 5 workloads. Use whenever the user asks which effort level to use ("what effort should this batch job run at?", "is xhigh worth it here?"), complains that Fable 5 is slow or expensive, wants to cut latency or token cost, designs a pipeline/harness that mixes routine and hard tasks, or reviews API code that sets output_config.effort.
What this skill does
Effort Calibrator
On Fable 5, effort is the primary dial trading intelligence against latency and cost. Defaults that were right for earlier models are usually wrong here: Fable 5 at lower effort frequently beats earlier models at xhigh, so over-provisioning effort wastes money and time without adding quality.
Starting points by workload
| Workload | Start at |
|---|---|
| Routine transforms, classification, short edits, chat, subagents | medium (try low if latency matters) |
| Most analysis and writing | high (the general default) |
| Coding and agentic/tool-heavy work | high (the API and Claude Code default on Fable 5) — even for workloads that ran at xhigh on earlier Opus models; escalate to xhigh only for the most capability-sensitive tasks |
| Hardest capability-sensitive work: large migrations, multi-day autonomous runs, novel research | xhigh |
Frontier problems only, where evals show headroom above xhigh and token spend is unconstrained | max |
max is rarely the right answer: on most workloads it adds significant cost for small gains and can tip into overthinking. Reach for it only when xhigh has measurably fallen short.
Adjustment signals
Lower effort when:
- Tasks complete correctly but take longer than the work warrants
- The session is interactive and waiting hurts more than marginal quality helps
- Output shows over-deliberation: long context-gathering before trivial actions
Raise effort when:
- First-shot correctness matters more than turnaround (one-way-door changes, unattended runs)
- The task benefits from rigorous self-verification, which higher effort does noticeably better
- A task failed at the current level in a way that looks like shallow reasoning, not missing information
Pipeline pattern
Route by task class, not by a single global setting: a triage step at low/medium that escalates hard cases to high/xhigh usually dominates any fixed choice on both cost and quality. For long agentic loops, effort composes with task budgets, an advisory token budget for the whole loop.
API shape
Set effort via output_config: {"output_config": {"effort": "low" | "medium" | "high" | "xhigh" | "max"}}. Setting high is equivalent to omitting the parameter. At high and xhigh, set a large max_tokens — it is a hard limit on total output, thinking plus response text. Verify parameter names and values with the current API reference before shipping: https://platform.claude.com/docs/en/build-with-claude/effort
Related skills
Word Document Editor
anthropics
Create, edit, and format Word documents with tables, images, and tracked changes.
Ask Questions If Underspecified
trailofbits
Ask clarifying questions before starting work on ambiguous requests.
CLAUDE.md Optimizer
daymade
Optimize your CLAUDE.md file for clarity, efficiency, and maintainability.
Claude Skills Troubleshooter
daymade
Diagnose and fix plugin installation, enablement, and activation problems.