Back to the catalog
published by agent-sh
47 tools
- agnixLint agent configurations before they silently fail. 414 validation rules across Claude Code, Codex CLI, OpenCode, Cursor, GitHub Copilot, G484 stars
- audit-projectMulti-agent iterative code review until zero issues remain. Spawns up to 10 specialist reviewers (code quality, security, performance, test 3 stars
- can-i-helpContributor guidance for any project — matches developer skills to data-backed contribution opportunities. `/can-i-help` collects project-he3 stars
- debateStructured multi-round debate between AI tools with proposer / challenger roles and a final verdict. `/debate` orchestrates a back-and-forth4 stars
- deslopDetect and remove AI-generated slop with certainty-based findings and safe auto-fixes. AI coding tools leave behind debug `console.log`s, `p8 stars
- drift-detectDeep repository analysis to realign project plans with actual code reality. `/drift-detect` discovers drift between documented plans (CHANGE4 stars
- enhanceMaster enhancement orchestrator: 7 specialized analyzers run in parallel and produce a unified report with certainty-graded findings. `/enha4 stars
- gate-and-shipQuality gates then ship — chains `/prepare-delivery` and `/ship` in one command. Runs the full pre-ship pipeline (deslop, simplify, agnix, e1 star
- learnResearch any topic online and create comprehensive learning guides with RAG-optimized indexes for your AI agents. `/learn react hooks` searc3 stars
- next-taskAutonomous workflow orchestrator that takes a task from discovery to production through 12 coordinated phases — exploration, planning, imple7 stars
- perfStructured performance investigation with baselines, profiling, and evidence-backed decisions — run by AI agents inside your editor. `/perf`3 stars
- prepare-deliveryPre-ship quality gates without the ship. Runs the full pre-merge pipeline — deslop (clean AI debris), simplify (de-bloat), agnix (lint agent2 stars
- repo-intelUnified static analysis for AI agents — git history, AST symbols, project metadata, doc-code sync, and (optionally) LLM-augmented file descr4 stars
- skillersLearn from your workflow patterns and suggest skills, hooks, and agents to automate the repetitive work. Skillers reads your AI conversation4 stars
- sync-docsDetect outdated documentation by comparing docs against actual code state — broken references, version mismatches, stale code examples, and 3 stars
- web-ctlBrowser automation toolkit for AI agents — navigate, authenticate, and interact with web pages through a single CLI. Agents drive headless b
- zig-lspZig language server for Claude Code via ZLS — automatic post-edit diagnostics, jump-to-definition, find-references, hover. Maps `.zig` and `
- consultCross-tool AI consultation. Use when user asks to 'consult gemini', 'ask codex', 'get second opinion', 'cross-check with claude', 'consult a1,016 stars
- debateStructured AI debate templates and synthesis. Use when orchestrating multi-round debates between AI tools, 'debate topic', 'argue about', 's1,016 stars
- deslopUse when user wants to clean AI slop from code. Use for cleanup, remove debug statements, find ghost code, repo hygiene.1,016 stars
- discover-tasksUse when user asks to "discover tasks", "find next task", "prioritize issues", "what should I work on", or "list open issues". Discovers and1,016 stars
- drift-analysisUse when the user asks about plan drift, reality check, comparing docs to code, project state analysis, roadmap alignment, implementation ga1,016 stars
- enhance-agent-promptsUse when improving agent prompts, frontmatter, and tool restrictions.1,016 stars
- enhance-claude-memoryUse when improving CLAUDE.md or AGENTS.md project memory files.1,016 stars
- enhance-cross-fileUse when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.1,016 stars
- enhance-docsUse when improving documentation structure, accuracy, and RAG readiness.1,016 stars
- enhance-hooksUse when reviewing hooks for safety, timeouts, and correct frontmatter.1,016 stars
- enhance-orchestratorUse when coordinating multiple enhancers for /enhance command. Runs analyzers in parallel and produces unified report.1,016 stars
- enhance-pluginsUse when analyzing plugin structures, MCP tools, and plugin security patterns.1,016 stars
- enhance-promptsUse when improving general prompts for structure, examples, and constraints.1,016 stars
- enhance-skillsUse when reviewing SKILL.md files for structure and trigger quality.1,016 stars
- learnResearch any topic online and create learning guides. Use when user asks to 'learn about', 'research topic', 'create learning guide', 'build1,016 stars
- orchestrate-reviewUse when user asks to "deep review the code", "thorough code review", "multi-pass review", or when orchestrating the Phase 9 review loop. Pr1,016 stars
- perf-analyzerUse when synthesizing perf findings into evidence-backed recommendations and decisions.1,016 stars
- perf-baseline-managerUse when managing perf baselines, consolidating results, or comparing versions. Ensures one baseline JSON per version.1,016 stars
- perf-benchmarkerUse when running performance benchmarks, establishing baselines, or validating regressions with sequential runs. Enforces 60s minimum runs (1,016 stars
- perf-code-pathsUse when mapping code paths, entrypoints, and likely hot files before profiling.1,016 stars
- perf-investigation-loggerUse when appending structured perf investigation notes and evidence.1,016 stars
- perf-profilerUse when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.1,016 stars
- perf-theory-gathererUse when generating performance hypotheses backed by git history and code evidence.1,016 stars
- perf-theory-testerUse when running controlled perf experiments to validate hypotheses.1,016 stars
- repo-intelUse when user asks to "run repo intel", "generate repo map", "analyze repo", "query hotspots", "check ownership", or "bus factor". Unified s1,016 stars
- sync-docsSync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after code change1,016 stars
- validate-deliveryUse when user asks to "validate delivery", "check readiness", or "verify completion". Runs tests, build, and requirement checks with pass/fa1,016 stars
- web-authAuthenticate to websites with human-in-the-loop browser handoff. Use when user needs to log into a website, complete 2FA, or solve CAPTCHAs 1,016 stars
- web-browseBrowse and interact with web pages headlessly. Use when agent needs to navigate websites, click elements, fill forms, read content, or take 1,016 stars
- agnixUse when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuratio484 stars
Looking for something else?QuestionsContact
