Every feature flag, and where it lived
62 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_1p_event_batch_config ◇ Default {}. Batch settings for Claude Code's first-party event logger: scheduledDelayMillis (falls back to OTEL_LOGS_EXPORT_INTERVAL, then 10000), maxExportBatchSize (default 200) and maxQueueSize (default 8192), plus skipAuth, maxAttempts, path and baseUrl passed to the exporter. When the value changes during a session, the logger is flushed and rebuilt with the new settings.never mined ·never mined AND v2.0.37
tengu_amber_flint ◇ Default true. A kill switch for agent teams: teams are enabled only when CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS is set or --agent-teams is passed, and this flag is on. Turning it off disables teams even when they were requested.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.33
tengu_amber_sentinel ◇ Default false. Gates the Monitor tool, which streams each output line of a background command to Claude as a notification; the tool is enabled only when this flag and a second runtime check both pass. When on, monitors declared by plugins are also started, the Bash and scheduled-task tool instructions point Claude at Monitor for waiting on a condition, and a Bash command with a long leading sleep is blocked.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.98
tengu_amber_wren ◇ Default {}. Object of default file reading limits used by the Read tool and other file reads: maxSizeBytes (default 262144), maxTokens (default 25000; CLAUDE_CODE_FILE_READ_MAX_OUTPUT_TOKENS above 0 takes precedence), includeMaxSizeInPrompt (when true, the Read prompt says files larger than the size limit return an error) and targetedRangeNudge (when true, the Read prompt tells the model to read only the part of a file it needs instead of recommending reading the whole file). Numbers that are not positive and finite fall back to the defaults, and the result is cached for the session.v2.1.138 or earlier → v2.1.267 ○gone AND v2.1.75
tengu_ashen_kelp ◇ No description from anybody.v2.1.138 or earlier → v2.1.140 ○gone AND v2.1.132
tengu_billiard_aviary ◇ Default false. When on, auto memory switches to a variant stored in a tiny_memory directory instead of memory under the project's folder in ~/.claude/projects/ (when no memory directory override is set), with its own memory prompt; it also changes several other memory code paths, for example adding a created date default to the frontmatter of memory files.v2.1.138 or earlier → v2.1.190 ○gone AND v2.1.94
tengu_birch_compass ◇ Default false. When on, the usage limits view adds a cost breakdown panel that scans local session files (showing Scanning local sessions… meanwhile) and, for a day or week window, lists the behaviours above a percentage threshold plus agents, skills and plugins, with tips. If any session file is over 200MB it shows Cannot compute breakdown instead.v2.1.138 or earlier → v2.1.148 ○gone AND v2.1.108
tengu_brass_condor_loupe ◇ A remote-config gate decides whether an internal UI element shows a summary view or stays hidden.v2.1.257 → v2.1.267 ○gone AND v2.1.257
tengu_bridge_host_profile ◇ A new setting controls how much machine info Remote Control shares when it registers a device.v2.1.260 → v2.1.308 ◆in the build AND v2.1.260
tengu_bridge_poll_interval_ms ◇ No description from anybody.never mined ·never mined AND v2.1.58
tengu_bridge_repl_v2 ◇ No description from anybody.never mined ·never mined AND v2.1.77
tengu_ccr_no_subscriber_hold_ms ◇ Remote-control worker connections gained tuning gates for an upload hold delay and for skipping redundant heartbeats.v2.1.259 → v2.1.308 ◆in the build AND v2.1.259
tengu_ccr_upload_trim ◇ A new telemetry gate fires when background-worker upload trimming occurs.v2.1.260 → v2.1.308 ◆in the build AND v2.1.260
tengu_cobalt_compass ◇ No description from anybody.never mined ·never mined AND v2.1.75
tengu_cobalt_plinth ◇ PR review artifact pages can show a pinned button that approves the pull request from your GitHub account.v2.1.172 → v2.1.308 ◆in the build AND v2.1.260
tengu_cobalt_plinth_sill ◇ A lock primitive's timeout can now be remotely tuned, though no server value is set yet.v2.1.260 → v2.1.308 ◆in the build AND v2.1.260
tengu_cobalt_raccoon ◇ No description from anybody.v2.1.138 or earlier → v2.1.152 ○gone AND v2.1.105
tengu_code_diff_cli ◇ No description from anybody.never mined ·never mined AND v2.1.50
tengu_collage_kaleidoscope ◇ No description from anybody.never mined ·never mined AND v2.1.73
tengu_dunwich_bell ◇ Default false. Gates the memory recall survey: when on, and Claude's latest reply cites a memory in a complete sentence of at most 250 characters, Claude Code may show that sentence under Claude recalled a memory: and ask How was Claude's recollection? (bad, fine or good), on a random sample whose rate is tengu_velvet_moth (code default 0.2). The survey stays off while CLAUDE_CODE_DISABLE_FEEDBACK_SURVEY is set or the allow_product_feedback policy disallows it.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.105
tengu_elegant_pancake ◇ The clipboard stash-and-restore around tool use is gone, leaving only a flag check for whether the behavior is on.v2.1.257 → v2.1.308 ◆in the build AND v2.1.257
tengu_event_sampling_config ◇ Default {}. A per-event sampling table for Claude Code's own analytics events, keyed by event name. When an event's entry has a numeric sample_rate between 0 and 1, a rate of 0 drops the event, a rate below 1 keeps it with that probability and adds sample_rate to the logged fields, and a rate of 1 logs it normally; a missing entry or an invalid rate also logs normally.never mined ·never mined AND v2.0.54
tengu_flint_harbor ◇ No description from anybody.never mined ·never mined AND v2.1.94
tengu_flint_harbor_share ◇ Default false. Turns on sharing for /team-onboarding: it enables the ShareOnboardingGuide tool, appends instructions for calling that tool to the command's prompt, and lets the team-onboarding-share tip be shown. Each of these also requires the allow_team_onboarding policy, an OAuth access token, and one further check to pass.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.128
tengu_grey_step2 ◇ No description from anybody.never mined ·never mined AND v2.1.68
tengu_gypsum_kite ◇ Default false. When on and the account is on the pro plan, the Opus entries in the model picker get · ~2× usage vs Sonnet appended to their description.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.91
tengu_harbor_ledger ◇ Default []. Built-in allowlist of channel plugins as {marketplace, plugin} entries; a value that fails validation counts as empty. When managed settings give no allowedChannelPlugins, a plugin requested through --channels outside development mode is skipped unless it is on this list. Separately, whatever the managed setting says, an MCP server's claude/channel capability is removed from its reported status unless its plugin is on this list (among other conditions).v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.80
tengu_harbor_permissions ◇ Default false. Turns on relaying permission prompts to channels: the interactive session registers a channel permission handler, and a tool permission prompt is sent as a notifications/claude/channel/permission_request (tool name, description, input preview) to each connected channel server from the session's --channels list that has registered for it. Tools that require user interaction are not relayed.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.81
tengu_hazel_osprey ◇ Default false. Turns on the context-hint-2026-04-09 beta for main-thread requests that carry first-party betas: once an estimate of savable tokens reaches 20000, the request body gets context_hint with enabled: true and a target_tokens_saved from tengu_hazel_osprey_floor (default 75000, omitted unless above 0). API errors such as 422, 424, 409, 529 or an invalid request turn the hint off again.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.110
tengu_heron_brook ◇ On some models Claude will stop spinning up subagents or research workflows unless you actually ask for it.v2.1.150 → v2.1.308 ◆in the build AND v2.1.257
tengu_jazzy_bird ◇ A gate that would skip commit and PR attribution text and suppress bridge conflict recovery defaults to off.v2.1.257 → v2.1.258 ○gone AND v2.1.257
tengu_kairos_input_needed_push ◇ Default false. Shows the Push when actions required toggle (the inputNeededNotifEnabled setting) in the settings list and the matching row in the Notifications panel; both places also need a further condition to hold.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.110
tengu_log_datadog_events ◇ Default false. When on, each analytics event that passes sampling is also sent to Datadog, in addition to the first-party event logger; Datadog only accepts it with the first-party API provider and for event names on a built-in list. A datadog: true entry in the remote sink-disable config turns it off regardless.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.0.36
tengu_madrone_spindle_corbel ◇ Publish results can note when an artifact was seeded from a comment thread, prompting a reply.v2.1.260 → v2.1.308 ◆in the build AND v2.1.260
tengu_marble_whisper ◇ No description from anybody.never mined ·never mined AND v2.1.70
tengu_mcp_discover_projection_prior ◇ A new gate resolves MCP discovery projection to legacy-only, all or off, and defaults to off.v2.1.259 → v2.1.308 ◆in the build AND v2.1.259
tengu_noreread_q7m_velvet ◇ No description from anybody.never mined ·never mined AND v2.1.91
tengu_onyx_plover ◇ Default null. Configures auto dream memory consolidation: enabled: true turns it on when the autoDreamEnabled setting is unset, enabled or available being true makes the feature available, and minHours (default 24) and minSessions (default 5) set how long and how many sessions must pass since the last consolidation before another runs. Non-positive or non-numeric values use the defaults.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.94
tengu_penguins_enabled ◇ No description from anybody.never mined ·never mined AND v2.1.36
tengu_pewter_ledger ◇ No description from anybody.never mined ·never mined AND v2.1.122
tengu_plank_river_frost ◇ No description from anybody.never mined ·never mined AND v2.1.14
tengu_polished_dewdrop ◇ A new hidden switch, settable via env var, can make certain responses silently drop or error instead.v2.1.263 → v2.1.308 ◆in the build AND v2.1.263
tengu_print_engine_loop ◇ The env var controlling print and engine loop behavior was renamed to CLAUDE_CODE_HUMBLE_HAMMOCK and still defaults to off.v2.1.247 → v2.1.252 ○gone AND v2.1.257
tengu_quiet_harbor ◇ Default false. Supplies the background daemon cold-start mode when neither CLAUDE_CODE_DAEMON_COLD_START (transient or ask) nor the daemonColdStart setting is set: true gives ask, false gives transient. With ask, when no background daemon is running and the install prompt has not been dismissed, Claude Code (under further conditions) returns an install request telling you to run claude daemon install instead of spawning a transient daemon.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.120
tengu_radiant_island ◇ A one-time prompt offering to switch your default effort to medium exists but has no text.v2.1.240 → v2.1.261 ○gone AND v2.1.263
tengu_review_bughunter_config ◇ The cloud review poll timeout is no longer hardcoded at 30 minutes and now comes from remote config.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.259
tengu_sage_compass ◇ No description from anybody.never mined ·never mined AND v2.1.98
tengu_slate_finch ◇ Default false. When on and the account's plan is pro, the effort messages (Set effort level to ... and Current effort level: ...) describe high with an added note that it burns fastest and that medium handles most tasks.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.91
tengu_slate_ribbon ◇ No description from anybody.never mined ·never mined AND v2.1.110
tengu_slate_siskin ◇ Config for the memory-write survey, default {enabled: false, timeoutMs: 8000, throttleMs: 30000, summaryLineThreshold: 5}; valid fields override the defaults, and a value that fails the schema is logged and ignored entirely. With enabled on (and product feedback allowed, among other checks), a main-agent write to a file directly inside the memory directory, other than MEMORY.md, is shown in an Approve/Reject dialog, and rejecting undoes the write. throttleMs spaces dialogs apart, the dialog closes with a timeout outcome after timeoutMs, and a write over summaryLineThreshold lines gets a one-sentence model summary.v2.1.138 or earlier → v2.1.161 ○gone AND v2.1.120
tengu_sm_config ◇ No description from anybody.never mined ·never mined AND v2.0.68
tengu_snippet_save ◇ No description from anybody.never mined ·never mined AND v2.1.59
tengu_sotto_voce ◇ No description from anybody.never mined ·never mined AND v2.1.66
tengu_sub_nomdrep_q7k ◇ No description from anybody.never mined ·never mined AND v2.1.91
tengu_swann_brevity ◇ No description from anybody.never mined ·never mined AND v2.1.66
tengu_tussock_oriole ◇ Default false. When on, the team-artifacts tip can show New from your team: ..., listing project skills and commands by teammates that the user has not seen yet, and skill names from project settings can show a · by <author> attribution. Off, neither appears.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.117
tengu_ultraplan_config ◇ Default null. /ultraplan and the other ultraplan entry points in the prompt input are enabled when this object's enabled field is true and two further checks pass; any other value leaves them off.v2.1.138 or earlier → v2.1.308 ◆in the build AND v2.1.91
tengu_usage_overage_included_models ◇ A display for overage-included models exists but has an empty allowlist until set remotely.v2.1.186 → v2.1.308 ◆in the build AND v2.1.261
tengu_vellum_lantern ◇ Default false. Turns on the alternate prompt mode that CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT controls, for eligible models (claude-opus-4-7, model IDs ending in -eap, or models listed in the simple_system_prompt client data or the tengu_velvet_cascade flag). -eap and listed models get the mode whether or not this flag is on, and a truthy or explicitly falsy CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT overrides both.v2.1.138 or earlier → v2.1.153 ○gone AND v2.1.120
tengu_willow_mode ◇ No description from anybody.never mined ·never mined AND v2.1.110
tengu_wise_comet ◇ Manual compaction now decides whether to strip thinking blocks, gated for adaptive thinking only.v2.1.260 → v2.1.308 ◆in the build AND v2.1.260
tengu_worktree_mode ◇ No description from anybody.never mined ·never mined AND v2.1.51
Nothing on this page matches that. Press Enter to search every feature flag.