nudge 0.1.0
/nudge <goal> applies behavioral design to a product or flow: diagnose why users don't act, design interventions that remove barriers, ranked hypotheses to test, and an ethics check on every answer. Its guide reaches Claude only when you run /nudge.
Vedant AndhaleInstall
/plugin marketplace add VedantAndhale/claude-pro-kit /plugin install nudge@claude-pro-kit
Run both lines inside Claude Code.
Hooks into
- Slash commands
Also in VedantAndhale/claude-pro-kit
-
turn-budget
0.4.0
When one turn uses more than +5 session points or 500,000 uncached input tokens, writes a handoff from exact session data and copies it for a new session; the old session is never cleared. No model calls.
Vedant Andhale in Status line, updated
4
-
session-receipt
0.2.0
/receipt opens a pane with the exact tokens every turn of the session spent (uncached, cached, output, subagents) and the costliest turns. No tokens spent.
Vedant Andhale in Panes, updated
4
-
pro-hud
0.3.1
Desktop heads-up display for the Pro plan: exact 5h/7d usage gauges, context gauge, turn receipts, usage in the spinner and compact tool cards. No estimates, no tokens spent.
Vedant Andhale in Usage & cost, updated
4
-
output-diet
0.2.0
Trims long shell output, Grep results and subagent reports before Claude reads them (head, tail and error lines kept); the untrimmed text is saved to a file Claude can open.
Vedant Andhale in Status line, updated
4
-
tool-diet
0.1.3
Moves tools you have not used lately behind ToolSearch, so their descriptions stop riding along on every request; core tools and anything you used in your last five sessions stay loaded.
Vedant Andhale in Status line, updated
4
-
context-xray
0.2.0
A pane with the exact breakdown of what fills Claude's context: system prompt, tools, memory files, skills, messages, and which tools load on every request.
Vedant Andhale in Panes, updated
4
-
reread-guard
0.2.0
Stops Claude re-reading a file it already read in this conversation, with Read or a plain cat, sed -n, head, tail or Get-Content, when the file has not changed since; a deliberate second attempt still goes through.
Vedant Andhale in Guardrails, updated
4
-
cache-clock
0.2.0
Shows how long the prompt cache stays warm, and when it expires, exactly how many tokens your next message will re-send uncached. No tokens spent.
Vedant Andhale in Status line, updated
4
-
read-cap
0.2.0
Stops Claude reading a file over 1,000 lines whole (with Read, cat or Get-Content) and gives it an outline tool (definitions with line numbers) so it reads only the range it needs. A retry still reads it whole.
Vedant Andhale in Status line, updated
4
-
budget-guard
0.1.0
Holds a prompt back once your 5-hour or weekly usage is at or over a limit you set (90% by default); sending it again goes through. No tokens spent.
Vedant Andhale in Usage & cost, updated
4
More commands mods
-
ruflo-arena
0.2.4
Competitive ruliology for Ruflo swarms — arenas, tournaments, and adaptive co-evolution of program strategies (ADR-147/148). Strategies-as-programs compete under payoff games; tournaments produce Wolfram-style competitive arrays; hill-climb and mutual co-evolution discover winners empirically.
ruvnet in Commands, updated
74.2k
-
subagent-models
0.1.0
Pins subagent models to a model-routing policy (Opus for judgement, Haiku for mechanical work, Sonnet otherwise) and logs every spawn.
escapeboy in Commands, updated
91
-
fable-pin
0.1.0
Pins every subagent to the fable model: rewrites the model on agent.spawn unless the spawn is a fork, with /fable-pin on, off and status. Touches nothing but its own store. Needs function hooks (early access).
Karan Bansal in Commands, updated
40
-
agent-meta
mod + skill
Meta-development tools for agentic workflows
technicalpickles in Commands, updated
10
-
orphan-server
0.3.1
Lists the servers a Bash call of the model started in this repository and left listening on a port, with their age and session, and stops one with SIGTERM, then SIGKILL.
Kerem Gok in Commands, updated
8