10/ 14·feed
LEGENDARY
TIER 5 / 5
SYNCEDOct 15 ’25Last re-publish — creators re-run the publish prompt to sync their rig.
claude-code·Opus + Sonnet (router)·ready
wall-of-glass
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.
91
/ 100Efficiency score 91 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 / MO38.0 MMonthly token burn — self-reported in the publish interview, not measured by the site.
SPEND / MO$120Monthly Claude spend — self-reported in the publish interview.
INSTANCES3+Concurrent 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.
MODELOpus + Sonnet (router)MODEL — Which Claude model powers this rig's default agent. Set via the /model command or the model setting.
Opus + Sonnet (router): Two model families used together — high-effort goes to Opus, routine work to Sonnet (inferred from usage).
Opus + Sonnet (router): Two model families used together — high-effort goes to Opus, routine work to Sonnet (inferred from usage).
INPUTvoiceINPUT — How you send prompts to Claude Code — keyboard, voice (via the built-in voice mode), or both.
voice: Voice dictation via Claude Code's built-in voice mode (Whisper transcription).
voice: Voice dictation via Claude Code's built-in voice mode (Whisper transcription).
THINKxhigh effortTHINK — Extended thinking effort — how deeply Claude reasons before responding. Toggled by Alt+T / /effort.
xhigh effort: Maximum reasoning depth — Opus 4.7's headline mode.
xhigh effort: Maximum reasoning depth — Opus 4.7's headline mode.
PLANplanPLAN — Exploration approach. Claude Code's permission modes: default (read + edit inline) or plan (read-only exploration → written plan → approval → edit).
plan: Plan mode — Claude explores read-only, writes a plan, you approve, then it edits.
plan: Plan mode — Claude explores read-only, writes a plan, you approve, then it edits.
MEMORYfrequent /clearMEMORY — Context discipline — how aggressively this rig manages the context window via /clear, /compact, and CLAUDE.md size. Not a single setting — a behavior pattern.
frequent /clear: Resets context aggressively with /clear between distinct tasks.
frequent /clear: Resets context aggressively with /clear between distinct tasks.
AUTOautoAUTO — Auto mode — whether Claude Code prompts for permission each time (default) or uses a background safety classifier to auto-approve (auto). Set via permissions.defaultMode.
auto: Background classifier auto-approves safe actions (research preview).
auto: Background classifier auto-approves safe actions (research preview).
VERIFYtests + Playwright + CIVERIFY — How this rig verifies Claude's changes — a discipline pattern (not a Claude Code setting). Tests, hooks, and CI all count.
tests + Playwright + CI: Tests + Playwright + GitHub Actions / CI gate before merge.
tests + Playwright + CI: Tests + Playwright + GitHub Actions / CI gate before merge.
PERMSsandboxed (auto-allow)PERMS — Permission model — how Claude Code requests (or skips) approval for actions. Set via permissions.defaultMode + permissions.allow list.
sandboxed (auto-allow): Bash + edits auto-approved within sandbox isolation (sandbox.enabled + autoAllowBashIfSandboxed).
sandboxed (auto-allow): Bash + edits auto-approved within sandbox isolation (sandbox.enabled + autoAllowBashIfSandboxed).
PHYSICAL · LOADOUT12 ITEMS
SHELLzsh · default·
MACHINEMac Studio M2 Ultra · 128GB·
EDITORVS Code·
+ DESK GEAR
DESKStanding desk·
LIGHTINGMonitor Light Bar·
BUILD · CLAUDE CODE CONFIG0 SKILLS · 0 PLUGINS · 0 HOOKS · 0 MCP · 1 SURFACES
HOOKS5+PostToolUse / PreToolUse / Stop
SURFACEClaude Code · CLI + Desktopprimary + secondary
+ the rest unlisted
BADGES
◇ Self-reported — attested in the publish interview.
runs 3+ Claude instances at once
◇ Self-reported — attested in the publish interview.
works in git worktrees
◇ Self-reported — attested in the publish interview.
5+ custom hooks
◇ Self-reported — attested in the publish interview.
standing desk
◇PARALLEL PROCESSOR
runs 3+ Claude instances at once
PARALLEL PROCESSOR◇ Self-reported — attested in the publish interview.
runs 3+ Claude instances at once
◇WORKTREE WIZARD
works in git worktrees
WORKTREE WIZARD◇ Self-reported — attested in the publish interview.
works in git worktrees
◇HOOK MASTER
5+ custom hooks
HOOK MASTER◇ Self-reported — attested in the publish interview.
5+ custom hooks
◇STANDING STRONG
standing desk
STANDING STRONG◇ Self-reported — attested in the publish interview.
standing desk
STATUSLINE · WHAT THEIR TERMINAL LOOKS LIKEclick to copy
CONFIG · 2 OF 9 SECTIONS · INDIVIDUALLY FORKABLEINSPECT ALL 2 IN DETAIL →
OPEN
SYSTEM PROMPT
1ITEM
INSPECT →⧉ EXPORT
OPEN
DESK
8ITEMS
INSPECT →↵
FREE SLOT
YOUR RIG HERE
+
PUBLISH YOURS →↵