max
A Claude Code settings key, read out of the shipped bundle. No mined inventory carries it: everything below comes from what this site has written about it.
The bundled Claude API skill docs now target the new Opus, covering thinking defaults, fallbacks and fast mode.
Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.219.
In the changelogs
30Releases whose published page names max.
-
v2.1.299
Usage breakdown gives advice on four more cost drivers
The usage breakdown now flags max effort, workflows, always-on context over 40k tokens and tool results over 10k tokens, with advice
found in this entry's text
-
v2.1.293
Effort levels are now defined in one shared list
Claude Code now keeps one shared list of effort levels: low, medium, high, xhigh and max
found in this entry's text
-
v2.1.290
/code-review mediumnow runs the high-effort recipe on most modelsOn every model without its own
/code-reviewrow, Opus 5.5 included,mediumnow runs the eight-angle high recipe instead of a single pass.high,xhighand Opus 5 are unchanged.found in this entry's text
-
v2.1.280
New "max effort" mode with /effort command
A new "max effort" mode appears with a footer hint pointing to the /effort command
found in this entry's text, named in this entry
-
v2.1.280
Max-effort reminder UI, gated off by default
A new reminder can appear in the status line when effort is set to max, pointing you to /effort to change it
found in this entry's text
-
v2.1.280
Max-effort reminder now shown as a warning when a CLI env var/flag is set
Max-effort reminder in the model panel turns into a warning-colored message when a specific env var or flag is set
found in this entry's text
-
v2.1.277
update_settings tool can now target more than localSettings, including userSettings.effortLevel
The internal update_settings tool can now write userSettings.effortLevel, not just localSettings
found in this entry's text
-
v2.1.274
Enterprise gateway: configurable Postgres connect timeout, retried boot connection, and rate-limit / X-Forwarded-For diagnostics
Enterprise gateway gets a configurable database connect timeout and clearer rate-limit/proxy warnings
found in this entry's text
-
v2.1.263
Effort-medium nudge generalized to multiple models and effort levels
The effort-downgrade nudge now works per model instead of just one, but each model needs its own flag turned on.
found in this entry's text
-
v2.1.260
AskUserQuestion tool gains typed answers and a follow-up mode
Questions to you can now be free-text or numeric, and can chain into follow-up questions.
found in this entry's text
-
v2.1.260
extendedQuestionsEnabled added to session config state
Extended question types are now gated behind a session-level flag rather than always on.
found in this entry's text
-
v2.1.260
AskUserQuestion tool gains richer question types and a 'more questions' path
Questions can now be free text or numeric, and follow-ups are preferred over Other/Skip options.
found in this entry's text
-
v2.1.260
AskUserQuestion telemetry can include extended per-question fields and a title
AskUserQuestion telemetry can now capture extended per-question fields and a title.
found in this entry's text
-
v2.1.257
New model: Mythos 5.1 added to model registry
Mythos 5.1 joins the model catalog with a 1M context window and effort levels up to max.
found in this entry's text, named in this entry
-
v2.1.257
Model effort levels (xhigh/max/regular) now derived from model metadata rather than a hardcoded model-name check
Which effort levels a model supports now comes from per-model metadata instead of matching model names.
named in this entry
-
v2.1.248
Reasoning effort levels and their aliases
Reasoning effort accepts low through max, with med and ultracode as aliases.
named in this entry, found in this entry's text
-
v2.1.248
Stale-work retry backoff gained a fourth input
One class of stale-work retry now backs off more gently on its own delay ladder.
found in this entry's text
-
v2.1.233
Bash and PowerShell tools can run under a memory limit on Linux
On Linux you can cap memory for shell commands so a runaway process cannot eat your machine.
found in this entry's text
-
v2.1.219
Bundled Claude API skill docs rewritten around Opus 5
The bundled Claude API skill docs now target the new Opus, covering thinking defaults, fallbacks and fast mode.
found in this entry's text
-
v2.1.219
New "Migrating to {{OPUS_NAME}}" migration guide with two breaking changes
A migration guide now spells out the two thinking-related changes that break existing API request code.
found in this entry's text
-
v2.1.197
Claude Sonnet 5 Is Now the Default Model
found in this entry's text
-
v2.1.136
Broader
/effort maxDocumentationfound in this entry's text
-
v2.1.128
Effort Selection Defaults Back to Auto
found in this entry's text
-
v2.1.126
Streaming idle-timeout calculation extracted into a helper
found in this entry's text
- v2.1.116
-
v2.1.111
New "xhigh" Effort Level
found in this entry's text
-
v2.1.76
/effortSlash Commandfound in this entry's text
-
v2.1.75
Plugin Configurable Options
found in this entry's text
-
v2.1.72
Effort Level "max" and Persistence
found in this entry's text
-
v2.1.38
Effort Level Control
found in this entry's text
First cited
0No release's published evidence quotes this name. The ledger indexes the Evidence lines of every changelog on this site, so this says nobody here has ever quoted it; it says nothing about how old the name is.
Presence across releases
0The miner has never read a build containing this name. It is here because a changelog entry of ours names it, which is evidence that it existed and not evidence of which releases carried it. The inventory starts at v2.1.138 and everything older than that was never mined.
Read out of the published npm bundle release by release, and out of Anthropic's own documentation as this site captured it. Nothing on this page is a description anybody here wrote about what the settings key does. All settings keys.