14/ 14·feed
LEGENDARY
TIER 5 / 5
SYNCED14d agoLast re-publish — creators re-run the publish prompt to sync their rig.
claude-code·Opus 5·ready
The Parallel Demon
VERIFIED
TOP 1%
SAMPLESample rig — an illustrative example seeded by howiclaude, not a real user submission. Rank is hidden because there's no real ranked population yet.
94
/ 100Efficiency score 94 of 100 — derived from analysis sub-scores (context discipline, automation depth, claude-md specificity, parallelism, permission hygiene)Top 1%·—·2 scored rigsBand is a fixed rubric curve for now — 2 real scored rigs on the site; true percentiles unlock with population.
EXPORT copies a prompt — paste it into your own Claude Code to install this rig.
TOKENS / MO52.0 MMonthly token burn — self-reported in the publish interview, not measured by the site.
SPEND / MO$160Monthly Claude spend — self-reported in the publish interview.
PLANMAX 20×Subscription tier — self-reported in the publish interview.
INSTANCES5Concurrent Claude Code instances they typically run — self-reported.
VOICESOMEShare of prompting done by voice instead of keyboard — self-reported.
SINCENOV ’24When they started using Claude Code — self-reported.
ACTIVITY · THE DAILY GRIND132 ACTIVE DAYS · LAST 180 DAYS
MONWEDFRI
FEBMARAPRMAYJUNJUL
TOKENS · ALL TIME640.0 MAll-time tokens — aggregated from local session logs by the publish prompt, not by the site.
CACHE HIT78%Prompt-cache hit rate over the aggregation window — measured from session logs by the publish prompt, not by the site.
STREAK12DConsecutive active days as of the last publish — from session logs, via the publish prompt.
BEST STREAK47DLongest run of consecutive active days — from session logs, via the publish prompt.
ACTIVE DAYS505/606Days with at least one session, over the days the logs span — via the publish prompt.
SESSIONS1.7 kTotal sessions found in the local logs — via the publish prompt.
MODEL MIX
OPUS 55% · SONNET 40% · HAIKU 5%
OPUS 55%SONNET 40%HAIKU 5%MODEL MIX — share of tokens by model family, straight from the rig's published usage data.
OPUS 55% · SONNET 40% · HAIKU 5%
≈ 10% OF ENGLISH WIKIPEDIALESSMORE
MODELOpus 5MODEL — The default model this rig runs (/model, or the `model` setting). Read from settings when published with the 2026-09 prompt; otherwise inferred from the usage mix.
Opus 5: Claude Opus 5 — the Max / Team / API default; 1M context, fast mode eligible.
Opus 5: Claude Opus 5 — the Max / Team / API default; 1M context, fast mode eligible.
EFFORTultracodeEFFORT — Effort level — how deeply Claude reasons per task (/effort, `effortLevel`). low → medium → high → xhigh → max; ultracode = xhigh + dynamic workflows; auto lets Claude pick.
ultracode: xhigh plus automatic dynamic workflows — Claude may orchestrate many agents for one task.
ultracode: xhigh plus automatic dynamic workflows — Claude may orchestrate many agents for one task.
PERMSautoPERMS — Permission mode — `permissions.defaultMode`. Auto mode (a background safety classifier approves safe actions) became Claude Code's default on 2026-08-14; Manual asks each time; plan is read-only until you approve a plan.
auto: Auto mode — the classifier approves routine actions, blocks the risky ones; hard_deny rules written as sentences. The 2026 default.
auto: Auto mode — the classifier approves routine actions, blocks the risky ones; hard_deny rules written as sentences. The 2026 default.
FLEET5× tmux · teams · cross-sessionFLEET — How many Claudes run at once, and what orchestrates them — tmux / cmux grids, the agent view (`claude agents`), the desktop app, or a GUI manager. Agent teams and cross-session messaging (2026-08) show here too.
their window layout┌─ claude ──────┬─ claude ──────┬─ claude ──────┬─ claude ──────┬─ ghostty ─────┐ │ feat/auth │ feat/payments │ chore/ci │ test/int │ tail logs │ └───────────────┴───────────────┴───────────────┴───────────────┴───────────────┘
their window layout┌─ claude ──────┬─ claude ──────┬─ claude ──────┬─ claude ──────┬─ ghostty ─────┐ │ feat/auth │ feat/payments │ chore/ci │ test/int │ tail logs │ └───────────────┴───────────────┴───────────────┴───────────────┴───────────────┘
LOOPS3 · /loop + /goal +LOOPS — Standing automations — /loop, /goal, routines (/schedule), saved dynamic workflows, Stop-hook loops. "My job is to write loops." One card per loop lives in the LOOPS deck below.
MEMORYauto memory · 72-line CLAUDE.mdMEMORY — What Claude remembers between sessions: auto memory (on by default since mid-2026, MEMORY.md + topic files) and the size of the global CLAUDE.md — the 2026 flex is a small one.
VERIFYtests + /code-review subagent + ChromeVERIFY — How this rig verifies Claude's work — the #1 official best practice in 2026: tests, /verify, /code-review, Stop hooks, Chrome or a simulator pane. In their words when published; otherwise inferred.
INPUTvoiceINPUT — How prompts get in — keyboard, voice (/voice hold or tap, or a dictation app), or both.
voice: Voice dictation via Claude Code's built-in /voice (or a dictation app like Wispr / Superwhisper).
voice: Voice dictation via Claude Code's built-in /voice (or a dictation app like Wispr / Superwhisper).
PHYSICAL · LOADOUT12 ITEMS
SHELLzsh · default·
MACHINEMacBook Pro 16" M3 Max · 64GB·
EDITORVS Code·
+ DESK GEAR
BUILD · CLAUDE CODE CONFIG3 SKILLS · 2 PLUGINS · 0 HOOKS · 2 MCP · 1 SURFACES
SKILLfive-tab-parallelspins up 5 worktree sessions on one feature
SKILLwriting-planswrites implementation plans before touching code
SKILLdispatching-parallel-agentsfans out independent subtasks to subagents
PLUGINsuperpowers
PLUGINfeature-devinstalled · not invoked
HOOKS5+PostToolUse / PreToolUse / Stop
MCPlinearfile issues from the terminal
MCPsentryinstalled · not wired
SURFACEClaude Code · CLI + Desktop + iOS + chromeprimary + secondary
BADGES
◇ Self-reported — attested in the publish interview.
runs 3+ Claude instances at once
5+ custom hooks
works in git worktrees
standing desk
7+ MCP servers
long Claude Code streak
◇ Self-reported — attested in the publish interview.
runs standing loops — /loop, /goal, routines
◇ Self-reported — attested in the publish interview.
agent teams, cross-session messaging, or a 10+ subagent fan-out as measured by the publish prompt
◇PARALLEL PROCESSOR
runs 3+ Claude instances at once
PARALLEL PROCESSOR◇ Self-reported — attested in the publish interview.
runs 3+ Claude instances at once
HOOK MASTER
5+ custom hooks
HOOK MASTER5+ custom hooks
WORKTREE WIZARD
works in git worktrees
WORKTREE WIZARDworks in git worktrees
STANDING STRONG
standing desk
STANDING STRONGstanding desk
MCP MAXIMALIST
7+ MCP servers
MCP MAXIMALIST7+ MCP servers
STREAK
long Claude Code streak
STREAKlong Claude Code streak
◇LOOP ENGINEER
runs standing loops — /loop, /goal, routines
LOOP ENGINEER◇ Self-reported — attested in the publish interview.
runs standing loops — /loop, /goal, routines
◇FLEET COMMANDER
agent teams, cross-session messaging, or a 10+ subagent fan-out as measured by the publish prompt
FLEET COMMANDER◇ Self-reported — attested in the publish interview.
agent teams, cross-session messaging, or a 10+ subagent fan-out as measured by the publish prompt
STATUSLINE · THEIR TERMINALTheir real statusline — captured from their settings.json statusLine by the publish prompt, shown as published.click to copy
CONFIG · 5 OF 10 SECTIONS · INDIVIDUALLY FORKABLEINSPECT ALL 5 IN DETAIL →
OPEN
SYSTEM PROMPT
1ITEM
INSPECT →⧉ EXPORT
OPEN
MCP
2ITEMS
INSPECT →⧉ EXPORT
OPEN
LOOPS
3ITEMS
INSPECT →⧉ EXPORT
OPEN
WORKFLOW
3ITEMS
INSPECT →⧉ EXPORT
OPEN
DESK
10ITEMS
INSPECT →↵
FREE SLOT
YOUR RIG HERE
+
PUBLISH YOURS →↵