read
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.
Skill listing and job tracking now go through the storage layer instead of touching files directly.
Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.223.
In the changelogs
45Releases whose published page names read.
-
v2.1.317
Artifact content Claude reads can now be marked in its results
For artifacts set to mark reads, what Claude reads through the artifact tool is now recorded and its results start with a marker
found in this entry's text
-
v2.1.314
Stricter safety checks for find, rg, sort, read, xargs and awk commands
Claude Code checks more shell commands more strictly before running them without asking, so some will now ask for permission
found in this entry's text
-
v2.1.312
Workshop pages and page-data reading removed from artifacts and plan mode
The artifact
read_page_dataaction and the plan-mode decision workshop and prototype offers are gone, and plan mode is read-only againfound in this entry's text
-
v2.1.311
Some shell commands that redirect using a variable they also set now ask permission
Claude Code now asks before running some shell commands whose redirect reads a variable set in the same command, and adds checks for zsh read
found in this entry's text
-
v2.1.311
Permission checks now look at the options of the shell
readcommandClaude Code now checks the options of the shell
readcommand, such as-a, when deciding on permissions, instead of skipping themfound in this entry's text
-
v2.1.311
Shell analysis of
readcan now skip settingREPLYClaude Code's shell analysis no longer always treats
readas settingREPLY; under one condition it skips that stepfound in this entry's text
-
v2.1.309
Changes to how Bash commands' variable assignments are tracked
Claude Code's reading of Bash commands now tracks variable assignments, including the
REPLYset byread, in a new wayfound in this entry's text
-
v2.1.292
Claude can list and read earlier versions of your artifacts
The Artifact tool gains a way to list an artifact's versions and to read a named earlier version, limited to artifacts you own
found in this entry's text
-
v2.1.287
Shell snapshots no longer need the cat command when the shell can do the copy itself
Shell snapshots now copy their helper commands using the shell's own built-in commands, and fall back to cat only when the shell cannot
found in this entry's text
-
v2.1.282
Reading an artifact's page data now shows when it followed an unattended auto-reply
The artifact tool's read_page_data action now carries the same "requested after an unattended auto-reply" note that read and verify already had
found in this entry's text
-
v2.1.281
Plugin hooks runtime gains a state library (atom/derive/memberOf/read/update)
The plugin function-hooks runtime gains a state library with atom, derive, memberOf, read and update
found in this entry's text
-
v2.1.281
Artifact read validation names the design tool in the not-a-URL message; publish may pre-fetch something
The artifact read action's not-a-URL error now names the design tool when it is available
found in this entry's text
-
v2.1.280
Skill/agent schema gains from_plugin field
An internal schema for skills and agents now has an optional from_plugin field
found in this entry's text
-
v2.1.277
Host filesystem bridge gains read/stat options and ancestor-search bound
Plugin filesystem read and stat calls gain configurable options, and ancestor search gets an optional lower bound
found in this entry's text
-
v2.1.275
'icon' field replaces deprecated 'favicon' in artifact publish, with new writer-access disclosure on read/list
Artifact icon field replaces the deprecated favicon parameter, and read/list now shows write access
found in this entry's text
-
v2.1.275
Artifacts read/list now reports and enforces writer vs viewer access
Artifact read/list actions now report and enforce whether you have edit access, not just view access
found in this entry's text
-
v2.1.275
artifact read: falls back to reading it as a frozen artifact type link on a 404
Reading an artifact that 404s now falls back to returning its type declaration if it's a frozen artifact type
found in this entry's text
-
v2.1.275
Artifact list/read results now report per-artifact writer access instead of an org-wide 'shared' bucket
Artifact permissions now check per-artifact edit access instead of whether you belong to the artifact's organization
found in this entry's text
-
v2.1.274
Reading public artifacts from outside your org now goes through a consent check instead of a flat block
Reading files from public, out-of-org artifacts now goes through a consent check instead of being flatly blocked
found in this entry's text
-
v2.1.271
"quickstart" artifact action added to the non-mutating action allowlist
The artifact tool's new "quickstart" action no longer requires write confirmation
found in this entry's text
-
v2.1.268
Artifact tool: list_files/read_file now resolve and return a
typeobject for type-locked filesArtifact file listing and reading now include the artifact's declared type when the file is type-locked
found in this entry's text
-
v2.1.268
Artifact read-permission denial path unified across list_files/read_file/verify/read actions
Artifact read-permission errors now use the same wording across list_files, read_file, verify, and read actions
found in this entry's text
-
v2.1.267
fs.readFile/fs.writeFile/fs.listDir renamed to fs.read/fs.write/fs.list; 'readFile' IPC event renamed to 'read'
File-system permission events renamed: fs.readFile/writeFile/listDir become fs.read/write/list
found in this entry's text
-
v2.1.265
Artifact tool actions being consolidated into list/read with a scope parameter
Artifact tool messages now describe actions as unified list/read calls with a scope, not old per-type names
found in this entry's text
-
v2.1.261
Per-URL ask/deny rules for artifact reads, page-data reads, diagnostics, and database reads
Artifact reads, diagnostics, and database reads now check per-URL deny/ask rules before falling back to session consent.
found in this entry's text
-
v2.1.261
Artifact tool 'verify' action gains an approval/target-changed check
Artifact verify actions now re-check approval before proceeding, matching other read actions.
found in this entry's text
-
v2.1.260
Artifact
get_endpoints/call_endpointactions renamed and scoped to remote-cowork entrypoints onlyRenamed endpoint actions remain invisible outside remote-cowork sessions.
found in this entry's text
-
v2.1.260
Artifact 'read' action's inline threshold made configurable
The artifact inline-read threshold is now configurable rather than fixed.
found in this entry's text
-
v2.1.260
Artifact read now passes a files-listed hint for artifact reads
Artifact reads now pass a hint indicating whether files were already listed.
found in this entry's text
-
v2.1.260
Artifact tool now enforces deny permission rules on all non-read actions
The artifact tool now checks deny rules before running any non-read action.
found in this entry's text
-
v2.1.259
Artifact pin/unpin — gated off by default
Artifacts gain full pin and unpin actions, wired end to end but off by default behind a gate with an env override.
found in this entry's text
-
v2.1.257
Artifact comments/watch tool renames its action vocabulary
Artifact comment actions are respelled: read replaces comments, watch with on false replaces unwatch, and old names now error.
named in this entry, found in this entry's text
-
v2.1.251
MCP auth now tracks which kind of login token it used
MCP connection failures now record which kind of login token was in play.
found in this entry's text
-
v2.1.248
Claude Design 403 message says whether your credential has access
A Claude Design 403 now says whether your credential actually grants access.
found in this entry's text
-
v2.1.239
Artifact tool gains a
readaction, with multi-file browsing and delete built but gated offClaude can now read back a published artifact's contents; browsing, multi-file publishing and deletion are built but off.
found in this entry's text
-
v2.1.239
Artifact failure messages point at the tool's own read action instead of WebFetch
Failed artifact publishes now tell Claude to re-read via the artifact tool, not WebFetch.
found in this entry's text
-
v2.1.239
Workflow tool gains run operations, with the auto-approval hook switched off
The workflow tool understands run-based commands that bypass the usual allow and deny rule lookup.
found in this entry's text
-
v2.1.228
Bundled SDK ships a runtime for server-managed agent work
The bundled SDK carries a worker that polls a server for agent work, unreachable from normal CLI use.
found in this entry's text
-
v2.1.223
Skills and jobs load through the storage sidecar
Skill listing and job tracking now go through the storage layer instead of touching files directly.
found in this entry's text
-
v2.1.182
Design MCP Connector Scope Auto-Expansion
found in this entry's text
-
v2.1.178
/design-login — Standalone Design-System Authorization
found in this entry's text
-
v2.1.174
Projects Tool — Read and Write claude.ai Project Docs
found in this entry's text
-
v2.1.169
/design-syncSkill — Sync React Design Systems to Claude Designfound in this entry's text
-
v2.0.50
MCP CLI Endpoint
found in this entry's text
-
v2.0.2
Fixed Stale Credential Cache
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.