Stats
Actions
Available In
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
By murillodutt
CELLM - Context Engineering for LLM-driven development. Structured specs, intelligent memory, and orchestration for AI agents building software.
Software architect specialized in Nuxt 4 and system design. Plans features, defines architecture, makes technical decisions, researches solutions, and writes specifications. Produces specs and decisions — never code.
Senior Nuxt 4 developer for implementing features and writing code. Implements features, creates components, builds APIs, and fixes bugs following project patterns and specs.
Project manager for task orchestration and status tracking. Creates tasks from specs, orchestrates execution via implementer agent, tracks progress, and reports status with dependency-aware ordering.
Senior code reviewer for quality assurance and verification. Reviews code against specs, checks for anti-patterns, validates security, and produces structured verification reports with severity-ranked findings.
Quality lab entrypoint with SCE-backed prove/debug/gate/stress flows. Use when: 'run tests', 'quality gate', 'debug this', 'stress test'.
Deep examiner for subsystem mapping and evidence-based findings with SCE envelope and write-back. Use when: 'argus on X', 'analyze block', 'map subsystem'.
Surgical fix engine with SCE-backed context, contract checks, and verifiable cure loop. Use when: 'cure this block', 'fix findings', 'asclepius on X'.
Bump project version and sync across all targets. Auto-discovers VERSION, package.json, plugin.json. Use when: 'bump version', 'bump', 'version bump', 'bump 0.36.0', or /sk-git delegates. NEVER during implement, orchestrate, asclepius, argus, hefesto, arena, or any code work.
Execute a real convergence loop — test the complete end-to-end pipeline with real data, identify failures, fix them, and repeat until total convergence. Concludes with full typecheck + root tests + Oracle tests. Use when: 'convergir', 'convergence loop', 'testar pipeline completo', 'e2e convergence', 'rodar tudo ate passar', 'loop de qualidade', 'validar tudo'. Also use proactively after large refactors, multi-file changes, or spec implementations that touch Oracle server code.
Admin access level
Server config contains admin-level keywords
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Marketplace with 3 plugins for Claude Code: cellm (core), docops (documentation), gdu (Goold Design UI).
Architecture: skills-only. No commands/ directories. Every capability is a skills/{name}/SKILL.md.
Context engineering for LLM-driven development. 29 skills, 4 agents, 6 hook events, Oracle integration.
| Skill | Activates on | What it enforces |
|---|---|---|
| typescript | *.ts, *.tsx, types/ | Strict typing, Zod validation, no any, explicit return types |
| drizzle | db/, schema.ts, drizzle.config | Typed schemas, .returning(), relations, transactions |
| dse | *.vue | Project-specific design tokens via dse_search before any UI work |
Context skills stack: editing a server/api/*.ts loads typescript.
| Skill | Invocation | What it does |
|---|---|---|
| init | /cellm:init [mode] | Interactive Oracle setup: install, status, update, doctor, restart, uninstall |
| plan | /cellm:plan [product] | Create mission.md, roadmap.md, tech-stack.md via guided Q&A |
| shape | /cellm:shape [feature] | Gather context and structure specs (requires plan mode) |
| write-spec | /cellm:write-spec [path] | Formalize shaping into technical spec (spec.md) |
| create-tasks | /cellm:create-tasks [path] | Break spec into task groups with dependencies |
| orchestrate | /cellm:orchestrate [path] | Execute tasks systematically, delegate to agents |
| implement | /cellm:implement [path] | Generate code from spec following patterns |
| verify | /cellm:verify [path] | Quality gate: spec compliance, security, patterns |
| spec | /cellm:spec [path] | Quick-create spec folder structure |
| spec-treat | /cellm:spec-treat [path] | Analyze spec for edge cases and inconsistencies |
| discover | /cellm:discover [focus] | Extract tribal knowledge into pattern files |
| inject | /cellm:inject [paths] | Inject relevant patterns into current context |
| index | /cellm:index [query] | Rebuild patterns index.yml |
| arena | /cellm:arena [mode] | Quality proving ground: prove, debug, gate, stress |
| oracle-search | /cellm:oracle-search <query> | Semantic search across Oracle observations |
| status | /cellm:status [verbose] | Quick Oracle worker health check |
| dse-discover | /cellm:dse-discover [path] | Bootstrap design system for a project |
| Agent | Model | Role |
|---|---|---|
| architect | opus | Plans features, defines architecture, writes specs. Never produces code. |
| implementer | sonnet | Implements features following specs and patterns. |
| project-manager | sonnet | Decomposes specs into tasks, orchestrates execution, tracks progress. |
| reviewer | sonnet | Reviews code against specs, patterns, and security standards. Read-only. |
| Event | What runs |
|---|---|
| SessionStart | ensure-oracle, /api/hooks/init, /api/hooks/context |
| UserPromptSubmit | capture-prompt, /api/knowledge/inject, /api/hooks/specs |
PreToolUse Edit|Write | /api/hooks/check-tags (workflow node lock detection) |
PreToolUse Write|Edit|Bash | version-guard (dependency version warning) |
PostToolUse Write|Edit|Bash|... | track-tool-use |
| PreCompact | capture-context |
| Stop | capture-context |
Worker daemon on port 31415. Auto-started on SessionStart.
Provides: semantic search, persistent memory, pattern discovery, knowledge base, OTEL metrics, DSE (Design System Engine), workflow graph, stack tracker.
Data: ~/.cellm/ (never in repo).
Documentation maintenance with LLM-first templates, code evidence, and drift control.
npx claudepluginhub murillodutt/cellm --plugin cellmGoogle Stitch design bridge — consumes DESIGN.md, HTML screens, and SITE.md artifacts into CELLM DSE, GDU Director, and orchestration workflows.
Observability and auditing plugin for Claude Code CLI Context Engineering
DocOps - Documentation maintenance workflows with LLM-first templates, code evidence, and drift control.
Goold Design UI (GDU): The definitive Vue 3, Nuxt 4, and Tailwind architect plugin. Enforces CELLM mantra: Verify before you act, document everything.
Portable engineering discipline, explicit project-stress prospecting, and code/domain knowledge mining for coding agents
murillodutt11 agents, 35 skills, 18 commands, 9 hooks — spec-driven multi-agent orchestration for Claude Code, with optional cross-device semantic memory.
komlukOpenAgentsControl — multi-agent orchestration for Claude Code. Context-aware development with skills, subagents, parallel execution, and automated code review.
darrenhindeDevelopment agents, skills, hooks, and commands for Claude Code workflows
b-open-ioHarness for Claude Code — skills, /harness:* slash commands, persona subagents, lifecycle hooks, and MCP tools without per-repo `harness setup`. Sibling plugins exist for Cursor, Gemini CLI, and Codex.
Intense-VisionsHigh-intelligence Claude Code copilot with deep code reasoning, evidence-driven planning, orchestration-first execution, model routing, context budgeting, CI/CD integration, enterprise security, plugin development, prompt engineering, performance profiling, agent teams, channels (event-driven autonomy with CI webhook, mobile approval relay, Discord bridge, and fakechat dev profile), interactive tutorials, LSP integration, security-hardened hook script library, MCP Prompts coverage, common workflow packs, runtime selection guide, computer-use patterns, checkpointing, scheduled-task blueprints, repo bootstrap scanner, hook policy engine (8 installable packs), layered memory deployment, role-based subagent packs (implementer, debugger, migration-lead, dependency-auditor, release-coordinator), 5 agent-team topology kits, autonomy operating mode (4 profiles + 3 gates), and a queryable 15-tool MCP documentation server with autonomy advisor.
markus41The complete library of Agent Skills — AI agents & orchestration, MCP & SDKs, Oracle & cloud, frontend & animation, engineering workflow, content & brand, and creative production. Skills auto-activate when relevant.
frankxai