burn-rate
claudeA fuel gauge above the prompt: context fill, tokens, dollars, dollars per hour, your plan's window, a sparkline of the last turns.
Refuses edits that replace code with a '... rest of the code' placeholder and tracks TODO stubs, debug prints and other leftovers above the prompt and in /slop.
Plugin slop-detector from marketplace slopshopper in ryx2/slopshopper. Commands read from the repo's manifest — 17 days ago.
No skills, commands, agents, hooks or MCP servers were found in the standard plugin folders.
Problems found in this repo's manifests
A fuel gauge above the prompt: context fill, tokens, dollars, dollars per hour, your plan's window, a sparkline of the last turns.
A ledger of files touched and commands run, counted on the spinner, printed as Markdown by /receipts.
Redacts API keys, tokens and private keys from tool results before Claude reads them, and refuses writes and commands that embed one.
Runs the test suite after every turn that changed source and keeps the result above the prompt.
Holds rm -rf, force pushes, git reset --hard, DROP TABLE, curl | sh, sudo and .env edits behind a question; refuses the unrecoverable ones.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
1 command · 6 agents
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.
DataHub development and interaction toolkit with connector planning, PR review, catalog search, metadata enrichment, lineage tracing, data quality management, and connection setup skills
13 skills · 8 commands · 4 agents
Create production-ready, editable PowerPoint decks through a spec-first, coordinate-explicit workflow with read-only reference analysis and quality gates.
5 skills · 1 agent
Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage
33 skills
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.