32 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 32 plugins that match these filters.
pskoett-skillspskoett/pskoett-ai-skills1
autoharnesstigerless-labs/autoharness1
wigtn-pluginswigtn/wigtn-plugins1
opendesignerckryptickunal/OpenDesigner1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplaceBuild, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs-goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).
Two-loop skill pipeline for Claude Code. Inner loop (plan-interview, intent-framed-agent, session-context, context-surfing, verify-gate, self-healing, simplify-and-harden) catches failures in-session — including active runtime recovery via self-healing when a command, test, build, helper, env, or external service fails mid-task. Outer loop (learning-aggregator, self-improvement, eval-creator, pre-flight-check) captures recurring patterns, promotes them to CLAUDE.md as permanent rules with human approval, and turns failures into regression tests. The harness gets stronger with every cycle.
Nightly offline self-evolution for this repo's Claude agent: harvests past Claude Code sessions (read-only), mines recurring tasks, replays them offline on your own API budget, and consolidates learnings into validated CLAUDE.md memory and SKILL.md skills behind a held-out gate, staged for review (never auto-applied). Verbatim vendor of microsoft/SkillOpt's stdlib-only skillopt_sleep engine + Claude Code plugin surface (MIT).
Per-symbol maintenance optimizer for an agent's skill layer — learns skills from real runs, keeps them by adherence in use.
Unified AI-native Vibe Coding plugin: PRD generation, digging analysis, screen-spec (IA / User Flow / Wireframe HTML / Dev Handoff), team-based parallel implementation, quality-gated auto-commit, 20 design styles, frontend (React/Next.js), backend (NestJS/Prisma), mobile (React Native/Expo), AI integration (STT/LLM), DevOps (Docker/CI-CD). 11 agents, 5 commands, 8 skills, team knowledge wiki (auto-collect + recall for WIGTN repos).
Nine skills: opendesigner (the interview), opendesigner-extract (learn from a reference without copying identity), opendesigner-extend (change a system safely), opendesigner-export (code, Figma, Paper), opendesigner-illustrate (open-licence illustrations recolored to your tokens), opendesigner-review (check a built UI at every size, theme, state and motion, with measurements and evidence), opendesigner-paint (original art and films painted in code in your palette), opendesigner-preflight (the silly mistakes to check before exporting anything visual), opendesigner-search (get a site found by search engines and AI answers).
designShared delivery practices for human–AI teams: planning, tickets, model selection, testing, independent review and release readiness. Install for a project or user; adopt project-owned authority and checks.
Drop-in ADR toolkit for AI coding agents: bootstrap and audit with /adr-kit:init, guided authoring with /adr-kit:adr, pre-commit and CI enforcement with file:line citations, context injection over a generated graph index, Guardian staleness detection, lifecycle commands, strict lint, adr-doctor, and a key-free MCP server.
Skills, rules, hooks, agents and output styles for Claude Code: test-gated landing for parallel agent work, framework knowledge with staleness verifiers, and security checks aimed at the agent itself
CLI toolbox for Observability-Driven Development (ODD): coding agents observe local runs on an OpenTelemetry/Grafana stack - or remote ones on any OpenTelemetry backend - and feed the next spec-driven improvement loop.
observabilityYour coding agent already plans and swarms — Wicked Garden is the curated toolkit for what it can't: proof-not-claims gates, code links grep can't see, deterministic refactor, cross-session memory, multi-model second opinions (fallback seats labelled). Don't fight the harness; fill its gaps. The gate needs wicked-vault (a self-contained infra peer, installed directly) and re-derives through garden's built-in engine; estate/bus are opt-in layers (wicked-testing and wicked-brain are retired — QE ships in-catalog as the qe domain, memory lives in wicked-estate).
PRD-CE methodology engine: scaffold (PRD/SoT/EPICs) + lifecycle skills + governance hooks + readiness scoring.
Build, configure, authenticate, extend, document, operate, upgrade, and contribute to Backstage applications and the Backstage core repository with current first-party workflows, safety gates, and migration guidance.
Open Horizons agentic DevOps platform toolkit for Azure, AKS, Backstage, AEG, GitHub, Azure DevOps, Terraform, security, reliability, architecture, and deployment operations. Use it to install specialist agents, reusable skills, safety hooks, MCP integrations, and a safe publisher for repository customizations.
9 quality-canary skills: rot-canary (code-health), gold-standard (world-class completeness), source-grounding (anti-hallucination), supply-chain-audit (deps/build/artifact), resilience-audit (failure-mode FMEA), telemetry-canary (observability), testability-canary (decoupling/DI), scale-canary (perf scaling), drift-canary (contract/schema drift). rot-canary adds cross-platform auto-cadence hooks. Served conformed from the committed plugin/ dist (built by scripts/build-plugin.mjs).
Five-stage, repo-agnostic feature pipeline: grill the decisions, author RFC/PRD, discover per repo, build against named proofs, then one adversarial audit gate. Plus /ef:ready: a deterministic gate that keeps the agent rulebook small and true.
developmentWarn-only, zero-dependency runtime harness layer for Claude Code (companion to superpowers): persistent state, scope control (prompt + action side), Default-FAIL verification & coverage gates, entropy governance (golden-rules + drift detection), and first-class C/C++ engineering (CMake/Meson/Make/Bazel + clang-tidy + sanitizers).
Coordination layer for multi-agent repositories. Gives task-pipeline runs leases with a TTL, race-free ID reservation, a cross-repo signal feed, an append-only run journal and a machine-generated read-only board. A lease is decided by a primitive that genuinely has compare-and-swap — an atomic file create on one machine, a pushed git ref across machines — never by the knowledge base, which loses concurrent writes; the store carries the record and the ID allocation, which is positional over the merged log. The knowledge backend is a pluggable adapter (Outline, filesystem) declaring its own capabilities and degrading out loud. Ships Claude Code hooks that deny edits to guarded registry files without a live lease.
developmentMemory-defragment/cleanup engine for agent memory, TWO lanes: class-B (memory + governance files) gets the semantic wash — a free mechanical Quick pass plus a code-enforced fidelity gate blocking any STRUCTURED-token drop by diff (links, dates, versions, frontmatter; prose fidelity is the paid semantic layer's job), consent-gated Full pass, every cut snapshot-backed (whole-run rollback); class-A (transcripts — the estate) gets byte-identity ULTRA archiving, never semantic-edited. Honest frame: slows how fast memory-overhead grows — it does not eliminate memory cost. Zero-dependency, offline, no API keys.
Self-contained agentic development harness: one command runs the full feature pipeline with double review and security gates.
