5/ 14·feed
EPIC
TIER 4 / 5
SYNCED18d agoLast re-publish — creators re-run the publish prompt to sync their rig.
claude-code·Opus 5·ready
solder-fumes
SAMPLESample rig — an illustrative example seeded by howiclaude, not a real user submission. Rank is hidden because there's no real ranked population yet.
82
/ 100Efficiency score 82 of 100 — derived from analysis sub-scores (context discipline, automation depth, claude-md specificity, parallelism, permission hygiene)Top 10%·—·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 / MO16.0 MMonthly token burn — self-reported in the publish interview, not measured by the site.
SPEND / MO$100Monthly Claude spend — self-reported in the publish interview.
PLANMAX 5×Subscription tier — self-reported in the publish interview.
SINCEJAN ’25When they started using Claude Code — self-reported.
MODEL MIX
OPUS 70% · SONNET 30%
OPUS 70%SONNET 30%MODEL MIX — share of tokens by model family, straight from the rig's published usage data.
OPUS 70% · SONNET 30%
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.
EFFORTxhighEFFORT — Effort level — how deeply Claude reasons per task (/effort, `effortLevel`). low → medium → high → xhigh → max; ultracode = xhigh + dynamic workflows; auto lets Claude pick.
xhigh: Deeper reasoning — the best setting for hard agentic work on the 5-class models.
xhigh: Deeper reasoning — the best setting for hard agentic work on the 5-class models.
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.
FLEET—FLEET — 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.
—: Not published — this rig predates the fleet fields.
their window layout┌─ neovim ───────┬─ claude ──────┐ │ current work │ current task │ └────────────────┴───────────────┘
—: Not published — this rig predates the fleet fields.
their window layout┌─ neovim ───────┬─ claude ──────┐ │ current work │ current task │ └────────────────┴───────────────┘
LOOPS—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.
—: No loops published yet.
—: No loops published yet.
MEMORYCLAUDE.md only · 118-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.
VERIFYnix flake check + the buildVERIFY — 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.
INPUT~ INFERREDmixed (kbd + voice)INPUT — How prompts get in — keyboard, voice (/voice hold or tap, or a dictation app), or both.
mixed (kbd + voice): Both — push-to-talk for long prompts, keyboard for quick edits.
~ Inferred from the score — this rig predates the 2026-09 prompt. Re-publish to show the real setting.
mixed (kbd + voice): Both — push-to-talk for long prompts, keyboard for quick edits.
~ Inferred from the score — this rig predates the 2026-09 prompt. Re-publish to show the real setting.
PHYSICAL · LOADOUT11 ITEMS
SHELLzsh · default·
MACHINECustom PC · 12th-gen Intel · 32GB · NixOS·
EDITORVS Code·
KEYBOARDa hand-wired QMK keyboard (40% ortho)·
+ DESK GEAR
MOUSEa trackball, name unknown·
DESKConvertible desk·
CHAIRa salvaged Steelcase Leap (v1, reupholstered)·
+ the rest unlisted
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
5+ custom hooks
◇ Self-reported — attested in the publish interview.
auto mode — the classifier approves, hard-deny rules hold the line
TINKERER
TINKERERHOOK MASTER
5+ custom hooks
HOOK MASTER5+ custom hooks
LINUX-USER
LINUX-USER◇AUTO-PILOT
auto mode — the classifier approves, hard-deny rules hold the line
AUTO-PILOT◇ Self-reported — attested in the publish interview.
auto mode — the classifier approves, hard-deny rules hold the line
STATUSLINE · THEIR TERMINALTheir real statusline — captured from their settings.json statusLine by the publish prompt, shown as published.click to copy
CONFIG · 2 OF 10 SECTIONS · INDIVIDUALLY FORKABLEINSPECT ALL 2 IN DETAIL →
OPEN
SYSTEM PROMPT
1ITEM
INSPECT →⧉ EXPORT
OPEN
DESK
8ITEMS
INSPECT →↵
FREE SLOT
YOUR RIG HERE
+
PUBLISH YOURS →↵