9/ 14·feed
EPIC
TIER 4 / 5
SYNCEDNov 30 ’25Last re-publish — creators re-run the publish prompt to sync their rig.
claude-code·Opus + Sonnet (router)·ready
fern-gully
SAMPLESample rig — an illustrative example seeded by howiclaude, not a real user submission. Rank is hidden because there's no real ranked population yet.
80
/ 100Efficiency score 80 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 / MO12.0 MMonthly token burn — self-reported in the publish interview, not measured by the site.
SPEND / MO$50Monthly Claude spend — self-reported in the publish interview.
FORKS1How many times this rig has been forked on howiclaude — counted by the site.
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).
INPUTmixed (kbd + voice)INPUT — How you send prompts to Claude Code — keyboard, voice (via the built-in voice mode), or both.
mixed (kbd + voice): Both — push-to-talk for long prompts, keyboard for quick edits.
mixed (kbd + voice): Both — push-to-talk for long prompts, keyboard for quick edits.
THINKhigh effortTHINK — Extended thinking effort — how deeply Claude reasons before responding. Toggled by Alt+T / /effort.
high effort: Deeper reasoning — for tricky multi-file refactors.
high effort: Deeper reasoning — for tricky multi-file refactors.
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.
MEMORYguided /compactMEMORY — Context discipline — how aggressively this rig manages the context window via /clear, /compact, and CLAUDE.md size. Not a single setting — a behavior pattern.
guided /compact: Runs /compact intentionally between tasks to keep working set focused.
guided /compact: Runs /compact intentionally between tasks to keep working set focused.
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 + PlaywrightVERIFY — How this rig verifies Claude's changes — a discipline pattern (not a Claude Code setting). Tests, hooks, and CI all count.
tests + Playwright: Test suite plus headless browser checks via Playwright.
tests + Playwright: Test suite plus headless browser checks via Playwright.
PERMSallowlistPERMS — Permission model — how Claude Code requests (or skips) approval for actions. Set via permissions.defaultMode + permissions.allow list.
allowlist: Specific commands are pre-approved via settings.permissions.allow.
allowlist: Specific commands are pre-approved via settings.permissions.allow.
PHYSICAL · LOADOUT12 ITEMS
TERMINALmacOS Terminal·
SHELLzsh · default·
MACHINEMacBook Pro 14" M3 Pro · 36GB·
EDITORVS Code·
+ DESK GEAR
DESKConvertible desk·
LIGHTINGString Lights·
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.
◇ Self-reported — attested in the publish interview.
5+ custom hooks
◇CONTEXT-KEEPER
CONTEXT-KEEPER◇ Self-reported — attested in the publish interview.
◇HOOK MASTER
5+ custom hooks
HOOK MASTER◇ Self-reported — attested in the publish interview.
5+ custom hooks
GREEN-THUMB
GREEN-THUMBLINEAGE → 1 downstream rigs
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
9ITEMS
INSPECT →↵
FREE SLOT
YOUR RIG HERE
+
PUBLISH YOURS →↵