caveman
claudeVendored, pinned copy of JuliusBrussee/caveman (MIT): ultra-compressed caveman-style replies that cut ~75% of output tokens while keeping technical substance exact.
7 skills · 3 agents · hooks
Plugin marketplace
A curated marketplace of cross-tool AI agent skills and plugins.
Add this marketplace
Then install any plugin below by name — each page has its exact command.
Vendored, pinned copy of JuliusBrussee/caveman (MIT): ultra-compressed caveman-style replies that cut ~75% of output tokens while keeping technical substance exact.
7 skills · 3 agents · hooks
Simple Technical English (ASD-STE100) bridged to caveman: caveman's compressed style stays the default, and STE takes over on exactly the turns caveman itself says to drop compression. Toggle with /ste:ste on|off|status.
2 skills · hooks
Build and run a decision board, a private claude.ai artifact with a database, where an agent posts questions and pending actions as cards and its operator answers from a phone instead of a terminal.
2 skills
Pause a Claude Code session before it burns through the 5-hour or 7-day usage window, wait for the reset without spending tokens, and resume automatically.
1 skill · hooks
Protocol for handing work to a subagent that cannot ask the human mid-run: delegate by default with two main-session carve-outs (secret values, human confirmations), a decision-completeness gate, stop-clause wording, an ask-and-continue variant for harnesses with a parent relay, and artifact verification instead of exit codes.
1 skill
One status line row for caveman, ste, and limit-guard: badges, vim mode, context, usage windows or session cost, prompt cache, model, agent, and PR. One python3 process, no chaining.
1 command
Delegate one unit of work to an agent in its own Herdr tab and drive that pane as a real terminal, for interactive prompts, live output and decisions the parent answers mid-run.
1 skill
Forge and drive a herd in Herdr: one agent per pane, panes as real terminals for interactive programs and live output, Claude panes started with permissions bypassed, other CLI agents on the same goal, a model and effort choice per role, turnover over compaction run by a steward, and a liaison that fronts the operator and writes the herd report.
1 skill
Optional evidence and review discipline for work where a wrong answer costs more than a slow one: measured-or-argued labels, three numbers and a control on every absence claim, the freeze and review gate, checker independence, and a rule budget.
1 skill
Drive a Korad KA3305P bench power supply through the korad CLI: guard, read-back on every write, unattended limits.
1 skill
Design, configure, audit, and troubleshoot MikroTik RouterOS networks — CAPsMAN/wifi, VLANs, firewall and multi-layer NAT, routing, DHCP, QoS, VPNs, and .rsc scripting.
1 skill
Drive an Ontrak ADU218 relay and opto-input box through the adu CLI: a channel is resolved from the operator's own wiring map or refused, the guard narrows the bench to one session's channels, and every write is read back.
1 skill
Controls for counting, searching and claiming absence across a corpus of files or binaries, so a sweep that did not run never reads as a clean zero.
1 skill
Shows how many plugins this repo ships, and links here.