bughunter
01Agent Claude Code
Proactive codebase scanner that hunts for bugs, dead code, vulnerabilities, and smells. Auto-detects stack. Reports only high-confidence findings.
not rated 4 2mo ago A 33 tokens
original MIT
cross-repo
02Agent Claude Code
Coordinates work that spans multiple repos simultaneously — API + frontend + services. Maps impact, sequences changes, and tracks dependencies across your project's repositories.
not rated 4 2mo ago A 32 tokens
original MIT
Agent Claude Code
Reference pattern for multi-phase orchestration. The MAIN Claude instance acts as coordinator — this file documents the protocol, not a separate agent to spawn.
not rated 4 2mo ago A 35 tokens
original MIT
Agent Claude Code
Adversarial verification agent. Independently proves work is correct by running checks. Auto-detects stack. Resolves obstacles proactively. NEVER trusts claims — only evidence.
not rated 4 2mo ago A 40 tokens
original MIT
Agent Claude Code
Audits and tunes the local Claude Code harness (hooks, agents, skills, settings, MCP) for reliability, cost, and throughput. Proposes minimal reversible config changes, never rewrites product code.
not rated 4 2mo ago B 46 tokens
original MIT
Agent Claude Code
Validates that code is production-ready — no mocks, no stubs, no fake data, real integrations only. Run before any deploy to staging or main.
not rated 4 2mo ago A 35 tokens
original MIT
tdd
07Agent Claude Code
Test-Driven Development specialist for Rails + Next.js stacks — RSpec (Rails) and Jest/Vitest (Next.js). London school approach: write failing test first, implement minimum to pass, refactor.
not rated 4 2mo ago A 45 tokens
original MIT
create-pr
08Command Claude Code
AXEL — Claude Code team configuration package. Additive bootstrap with hooks, agents, commands, skills, and plugins.
not rated 4 2mo ago A 0 tokens
original MIT
daily
09Command Claude Code
Scan rápido de todo lo que pasó desde el último check. Read-only, no escribe en ningún sistema. Diseñado para arrancar el día en 2 minutos sabiendo qué pasó y qué necesita atención.
not rated 4 2mo ago A 0 tokens
original MIT
deslop
10Command Claude Code
Check the diff against main and remove all AI-generated slop introduced in this branch.
not rated 4 2mo ago A 0 tokens
original MIT
Command Claude Code
Help me structure a message for a difficult or important conversation.
not rated 4 2mo ago A 0 tokens
original MIT
eod-review
12Command Claude Code
Generate an end-of-day report with everything that was done, changed, or moved TODAY. Designed to give non-technical stakeholders (CEO, PM, CS lead) clear visibility into delivery progress without requiring them to read PRs or Linear.
not rated 4 2mo ago A 0 tokens
original MIT
execute-prp
13Command Claude Code
Ejecuta el PRP especificado: $ARGUMENTS.
not rated 4 2mo ago A 0 tokens
original MIT
generate-prp
14Command Claude Code
Lee INITIAL.md en el directorio actual y genera un PRP (Product Requirements Prompt) completo que sirva como blueprint de implementación autosuficiente.
not rated 4 2mo ago A 0 tokens
original MIT
Command Claude Code
Coordinate a feature that spans multiple repos. Creates a parallel work plan and sequences changes correctly.
not rated 4 2mo ago A 0 tokens
original MIT
roadmap
16Command Claude Code
Analyze the codebase and generate a roadmap of potential features and improvements.
not rated 4 2mo ago A 0 tokens
original MIT
Command Claude Code
The heaviest command. Ingests Linear + Git across all configured repos + Slack (channels + DMs) — plus optional Notion and Intercom if your team uses them — deduplicates, and writes the consolidated state back into Linear (creating missing issues, updating statuses, reassigning based on git authorship). Then produces…
not rated 4 2mo ago A 0 tokens
original MIT
style
18Command Claude Code
Switch AXEL's response style for the current session.
not rated 4 2mo ago A 10 tokens
original MIT
visualize
19Command Claude Code
Use Mermaid diagrams to visualize the data lineage, architecture, or flow of the referenced code or project.
not rated 4 2mo ago A 0 tokens
original MIT
Skill Claude CodeCodex
Audits Claude Code context consumption across agents, skills, commands, hooks, MCP servers, and the CLAUDE.md/MEMORY chain. Identifies bloat and redundancy, then produces prioritized token-savings recommendations. Backs the /context-budget command.
not rated 4 2mo ago A 55 tokens
original MIT
Skill Claude CodeCodex
Review, optimize, and maintain the persistent memory system. Reads all memory files, identifies stale/duplicate/outdated entries, asks the user targeted questions, and produces a clean, optimized memory state. Use when memory feels bloated, after major project changes, or periodically to keep context sharp.
not rated 4 2mo ago A 61 tokens
original MIT
Skill Claude CodeCodex
Routes each subagent to the right model tier (fable, opus, sonnet, haiku) when orchestrating multi-agent work via the Agent tool or Workflow. Use whenever spawning 2+ agents or activating Coordinator Mode. Keeps judgment on Fable (main thread), delegates token-heavy work to cheaper tiers, and enforces handoff packets…
not rated 4 2mo ago A 80 tokens
original MIT
Skill Claude CodeCodex
Weekly PostHog analytical review. Pulls raw data from your PostHog project, identifies anomalies, regressions, and improvement opportunities, suggests new instrumentation and cohorts, then writes a condensed snapshot that other commands (sprint-status, eod-review, daily) can read for the next 14 days.
not rated 4 2mo ago B 67 tokens
original MIT
Skill Claude CodeCodex
UI/UX design intelligence. 67 styles, 96 palettes, 57 font pairings, 25 charts, 13 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing…
not rated 4 2mo ago B 221 tokens
copy · 98% MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: