Guard for dangerous shell commands: blocks the catastrophic and stops the risky for a person to run or confirm.
Plugin bulkhead from marketplace drydock in PabloMarquess/drydock. Commands read from the repo's manifest — 10 days ago.
No skills, commands, agents, hooks or MCP servers were found in the standard plugin folders.
A row per subagent, workflow agent, Kiro run (kiro-cli chat) and background task: Pixel Clawd or Kiro's ghost in a costume (random by default), a submarine for background tasks, with running, finished and failed counts, time and a memory warning from 70% (/deck details adds cost, requests, tokens processed, memory and Kiro's credits), and a dithered progress band above the prompt while they run.
Band above the prompt: turn, output speed, turn and session cost, prompt cache countdown and context fill.
Conversation theme for the desktop app: a tinted reply with an accent strip, a blue prompt, code cards and tool rows colored by kind.
Where Claude got its context, turn by turn: skills, MCP calls, files, web, subagents and what each used, shell programs and instruction files, with estimated tokens. A dim line under each reply and a timeline pane whose groups expand to list their sources; spends no model tokens.
Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and adds no policy of its own; one managed option, allowManagedModsOnly, limits mods to the organization's.
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Claude Code mod: watch Headroom snip tokens off every request, with an animated band, a /headroom log and a running total.
Optional mods companion for claude-seo (needs Claude Code 2.1.287+). A spend guard that holds paid SEO API calls against the claude-seo budget, and zero-token /seo-spend and /seo-doctor commands.
Optional local Claude Ads workbench for runs, evidence, inputs, comparison and report receipts. Enabled separately.
Mod almost any game you own with an AI agent: engine recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos, and a shared knowledge base of how games were modded.
13 skills · 3 agents · 1 MCP server · hooks
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.