caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Enforces that all Claude Code work is tracked as a beads task, and attaches per-task cost, token and duration attribution from ccusage
Plugin abacus from marketplace abacus in thijs-hakkenberg/abacus. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
cost-reportReport what recent beads tasks cost, from the abacus_* attribution metadata on the issues themselves
task-auditFind work that was never claimed or never attributed, and repair the metadata gaps that have exactly one correct fix
/abacus:acknowledgeShow what abacus would do on this machine, and switch governance on or off
/abacus:auditCheck whether any work is unclaimed or unattributed, and repair the metadata gaps that have exactly one correct fix
/abacus:statusShow what task is being tracked, whether the gate would allow an edit, and why not
/abacus:task-doneClose the task in progress, which writes its cost, token, duration and model attribution
/abacus:task-startClaim an existing beads task, or create and claim a new one, so edits are attributable
abacus-auditorReviews whether any work is unclaimed or unattributed, repairs the metadata gaps that have exactly one correct fix, and proposes concrete actions for the ones needing a decision. Use when asked to check tracking coverage, find untracked work, sweep for unclaimed tasks, or reconcile git activity agai
command -v python3 >/dev/null 2>&1 && python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session_start.py" || python "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session_start.py"
command -v python3 >/dev/null 2>&1 && python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/gate_edits.py" || python "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/gate_edits.py"
command -v python3 >/dev/null 2>&1 && python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/watch_bd_commands.py" || python "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/watch_bd_commands.py"
command -v python3 >/dev/null 2>&1 && python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/prompt_statusline.py" || python "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/prompt_statusline.py"
command -v python3 >/dev/null 2>&1 && python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/stop_reconcile.py" || python "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/stop_reconcile.py"
command -v python3 >/dev/null 2>&1 && python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session_start.py" --precompact || python "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session_start.py" --precompact
command -v python3 >/dev/null 2>&1 && python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session_end.py" || python "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/session_end.py"
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.