Every feature flag, and where it lived
41 of 2,081 feature flags One tick per build on this box, oldest on the left. A gap is a build the feature flag was not in.
State
This account
Anonymous
Compiled default
A is the one account this site reads, N the anonymous baseline, D what the release compiled in. 1,143 of 2,081 gates have been read at all: a run only records the gates its own release wrote about. Claude Code evaluates its gates on Anthropic's servers, so a reading of off can be a rollout this account sits outside of, and none of it says anything about your install. How to read these.
○ not in v2.1.308, ◇ we found no documentation describing it.
Feature flagWhat it doesSpan v2.1.138 → v2.1.308 Status Reading
tengu_anchor_tide ◇ Default false. Sets where the cursor lands when stepping back through prompt history: off places it at the start of the recalled prompt, on places it at the end.v2.1.152 → v2.1.156 ○gone AND v2.1.308
tengu_basalt_meadow ◇ Default false. When on, each prompt submission sends a tengu_render_glyph_cardinality telemetry event with the terminal renderer's style-pool size and glyph-atlas key count, plus the terminal program and a session-age bucket, and glyph-atlas recording stays on even when tengu_xterm_atlas_reset is off.v2.1.154 → v2.1.308 ◆in the build AND v2.1.308
tengu_bridge_placeholder_sweep ◇ Default true. Gates Remote Control placeholder bookkeeping: recording placeholder session ids in the replBridgePlaceholders config map (newest 20 kept), and a once-per-process sweep, 15 seconds after start, that looks at records older than 5 minutes whose owning Claude Code process is no longer running, archives a placeholder session that was never updated after creation, and drops records whose session is gone, was used, was archived, or is older than 30 days. false turns both off.v2.1.217 → v2.1.280 ○gone AND v2.1.308
tengu_ccr_delta_rehydrate ◇ Default false. Used when resuming a remote (CCR v2) session from its internal events. When off, the resume records the fallback reason client-gated and reads the events without a starting event id. When on, it looks up a stored event id for the session and, if that id appears in the last 64 KiB of the local transcript, passes it to the internal event reader so reading starts from that event; otherwise it falls back with the reason no-sidecar or tip-not-in-tail.v2.1.181 → v2.1.259 ○gone AND v2.1.308
tengu_ccr_plugins_turn_start_check_enabled ◇ No description from anybody.v2.1.299 → v2.1.306 ○gone AND v2.1.308
tengu_compass_dial ◇ Default false. When true, browsing prompt history shows a dim position label at the top of the prompt box, History N/M (or History while the total is not yet known), and Claude Code counts the history entries to fill in the total.v2.1.157 → v2.1.177 ○gone AND v2.1.308
tengu_compiled_acorn ◇ A new flag controls how poll and mid-turn event text is formatted.never mined ·never mined AND v2.1.308
tengu_cosmic_shore ◇ Default true. When on, a shell command running in the background is stopped once it passes a deadline, capped at 2 hours (or BASH_MAX_TIMEOUT_MS if larger): a command started with run_in_background uses its timeout if given, and otherwise, or when a command is moved to the background later, the deadline is 30 minutes (or BASH_DEFAULT_TIMEOUT_MS if larger); the message telling Claude a command moved to the background can then say when it will be stopped. When off, or when the background deadline is disabled for the session, backgrounded commands get no such deadline, and commands started by Monitor never get it.v2.1.285 → v2.1.308 ◆in the build AND v2.1.308
tengu_dash_flame ◇ No description from anybody.v2.1.219 → v2.1.308 ◆in the build AND v2.1.308
tengu_deferred_stub_tool ◇ Default true, read once per session and then kept. When on and deferred tool loading is in use, a request's tool list gains a tool named DeferredToolPlaceholder with defer_loading set, described as Reserved placeholder that keeps deferred tool loading active; never call this tool., unless one is already there. It is never added under HIPAA restrictions, or while CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS is set and tool search is not forced on.v2.1.207 → v2.1.308 ◆in the build AND v2.1.308
tengu_elegant_ocean ◇ New system-prompt text explains the sandbox's boundaries to the model, gated behind an unread flagnever mined ·never mined AND v2.1.308
tengu_event_watchdog_default_on ◇ No description from anybody.v2.1.169 → v2.1.195 ○gone AND v2.1.308
tengu_fg_left_arrow_agents ◇ Default false. Turns on the left-arrow shortcut to the agents view, which is also on once the global config has hasUsedAgentsFleet set; both paths also require a local (non-remote) workspace and agent view not being disabled by CLAUDE_CODE_DISABLE_AGENT_VIEW or the disableAgentView setting. When active, the footer can show a ← for agents hint, the left arrow key can open the agents view, and the config panel gains a ← opens agents toggle (leftArrowOpensAgents, default true) that turns the hint and the key off.v2.1.138 or earlier → v2.1.153 ○gone AND v2.1.308
tengu_fizzy_petal ◇ No description from anybody.v2.1.288 → v2.1.308 ◆in the build AND v2.1.308
tengu_gentle_hammock ◇ Remote Control requests can be gzip-compressed, but it is switched off in this build.v2.1.247 → v2.1.308 ◆in the build AND v2.1.308
tengu_glimmering_glade ◇ Remote control re-registers and reattaches your sessions if the server forgets this machine.v2.1.242 → v2.1.308 ◆in the build AND v2.1.308
tengu_gouda_loop ◇ Default false. When true, Claude Code checks for your closed issues on anthropics/claude-code: it reads a cached list and, at most once per 24 hours, runs gh issue list -R anthropics/claude-code --author @me --state closed, then shows a low-priority notice such as Your issue #N has been closed. Thanks for reporting! for issues not yet acknowledged and records them as acknowledged.v2.1.138 or earlier → v2.1.245 ○gone AND v2.1.308
tengu_joyful_globe ◇ No description from anybody.v2.1.259 → v2.1.308 ◆in the build AND v2.1.308
tengu_lexical_crystal ◇ No description from anybody.v2.1.287 → v2.1.308 ◆in the build AND v2.1.308
tengu_luminous_whistle ◇ Reasoning text from a non-Claude model can survive a model switch, off unless enabled.v2.1.251 → v2.1.278 ○gone AND v2.1.308
tengu_mcp_claudeai_eligibility_gate ◇ Default false. When on, a claude.ai connector (claudeai-proxy MCP server) whose config has eligible: false is not connected and is reported as needs-auth.v2.1.212 → v2.1.308 ◆in the build AND v2.1.308
tengu_mcp_stateless_skip_init ◇ Default true. When on, a claude.ai connector (claudeai-proxy) with stateless: true connects statelessly: MCP initialize is answered from its cached init response when that parses and carries a supported protocol version (otherwise a real initialize runs), and when tengu_mcp_discover_projection_prior is not off, server/discover can be resolved from a cached projection. It also turns on the anthropic-mcp-client-capabilities and MCP-Protocol-Version request headers even when tengu_mcp_discover_projection_prior is off.v2.1.169 → v2.1.308 ◆in the build AND v2.1.308
tengu_mossy_lantern ◇ Tools added or removed mid-conversation can be surfaced to the model, but the beta capability is gated off by default.v2.1.257 → v2.1.268 ○gone AND v2.1.308
tengu_native_cursor ◇ Default false. When true, Claude Code uses the terminal's native cursor, the same as setting CLAUDE_CODE_NATIVE_CURSOR, provided the DECSTBM renderer is not in use; the result is cached for the process. CLAUDE_CODE_ACCESSIBILITY and one other internal condition turn the native cursor on without this flag. On Windows the same switches also feed a second terminal setup check that does not look at the DECSTBM renderer.v2.1.163 → v2.1.308 ◆in the build AND v2.1.308
tengu_per_turn_effort ◇ Per-family capability gates now use a name-to-flag table instead of matching skill and tool name strings.never mined ·never mined AND v2.1.308
tengu_pewter_orchard ◇ No description from anybody.v2.1.210 → v2.1.231 ○gone AND v2.1.308
tengu_pewter_summit ◇ No description from anybody.v2.1.145 → v2.1.308 ◆in the build AND v2.1.308
tengu_polished_lagoon ◇ One session could inject a coordination notice into another, but three separate gates keep it dark.v2.1.234 → v2.1.308 ◆in the build AND v2.1.308
tengu_quartz_pipit ◇ Default true. When a main-thread turn under an active /goal ends in a way Claude Code classifies as unrecoverable (a context limit such as prompt_too_long or blocking_limit), the goal is cleared, its Stop hook removed, and the warning Goal cleared after an unrecoverable error (...) is shown. When false, that case returns without clearing the goal.v2.1.234 → v2.1.308 ◆in the build AND v2.1.308
tengu_rewind_first_message ◇ Default false. Changes the SDK rewind_conversation control request: when false, the rewind is anchored at the nearest assistant message before the target and fails with no preceding assistant if there is none. When true, it is anchored at the nearest user or assistant message before the target, that error is not returned (so the first message can be the target), and the anchor is persisted with { rewound: true }.v2.1.191 → v2.1.245 ○gone AND v2.1.308
tengu_slate_fern ◇ Default false. Turns on the unused plugin check: user-installed marketplace plugins not used for at least days days and sessions sessions feed the plugin-disuse-review startup tip (You haven't used the ... plugin in a while) and the days-since-last-use shown in the plugin list. Plugins that provide LSP servers, themes, output styles, monitors or workflows are never flagged, and the check is off when the strictKnownMarketplaces policy is set. true uses 14 days and 10 sessions; an object can set numeric days and sessions, each falling back to those values.v2.1.172 → v2.1.186 ○gone AND v2.1.308
tengu_slate_kestrel ◇ Default false. When on, a claude.ai OAuth login with no known subscription type (null) counts as eligible for organization policy limits; otherwise an OAuth login is eligible only on an enterprise or team subscription. A login with an API key is eligible either way, and the other checks (first-party API, the token's scope) still apply.v2.1.138 or earlier → v2.1.148 ○gone AND v2.1.308
tengu_slate_meadow ◇ Default false. When true, enables the background-agents fleet gate (isAgentsFleetEnabled) and adds the built-in Claude agent to the built-in agent list, unless agent view is disabled: by CLAUDE_CODE_DISABLE_AGENT_VIEW, the disableAgentView setting, or a third-party API provider. Both are also on without the flag when Claude Code runs in essential-traffic-only mode (for example with CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC set).v2.1.138 or earlier → v2.1.140 ○gone AND v2.1.308
tengu_slate_quill ◇ Default false. One of the gates for the DesignSync tool and the /design, /design-consent, /design-revoke and /design-login commands. They are off when the allow_design_sync policy check fails or another internal check disables them, on when a further internal check passes, and otherwise follow this flag.v2.1.160 → v2.1.245 ○gone AND v2.1.308
tengu_slim_subagent_claudemd ◇ Default true. When on, subagents whose definition sets omitClaudeMd (the built-in Explore and Plan agents in this version) start without the CLAUDE.md content in their user context, unless the caller passes its own user context. When off, they receive the CLAUDE.md content like other subagents.v2.1.138 or earlier → v2.1.195 ○gone AND v2.1.308
tengu_sorrel_trellis_lintel ◇ A comment sent moments before a watch starts could get a reply, but the flag is off.v2.1.236 → v2.1.267 ○gone AND v2.1.308
tengu_streaming_tool_execution2 ◇ Default false. Turns on streaming tool execution in the query loop: tool calls are handed to an executor as their tool_use blocks arrive while the model's response is still streaming, completed results are emitted during the stream, and the remaining results are collected after it ends. The executor is discarded and recreated when a response is retried or restarted.v2.1.138 or earlier → v2.1.153 ○gone AND v2.1.308
tengu_tingly_hopper ◇ Always-loaded claude.ai MCP tools are held out of the declared tool set and loaded lazily until the tool-use decision settles.v2.1.257 → v2.1.267 ○gone AND v2.1.308
tengu_valiant_lantern ◇ Six features controlled from Anthropic's servers are now checked early at startup, and five are off unless switched on remotelyv2.1.300 → v2.1.308 ◆in the build AND v2.1.302
tengu_witty_firefly ◇ No description from anybody.v2.1.301 → v2.1.306 ○gone AND v2.1.308
tengu_xterm_atlas_reset ◇ Default true. Enables proactive glyph atlas resets in the terminal renderer on xterm.js terminals: once 2000 distinct styled glyph keys have been recorded (and 2000 ms have passed since the last reset), and when the terminal regains focus, Claude Code writes the escape sequence \x1B]104;255\x07 and clears its glyph record. When off, glyph recording also stops unless tengu_basalt_meadow is on.v2.1.154 → v2.1.308 ◆in the build AND v2.1.308
Nothing on this page matches that. Press Enter to search every feature flag.