15 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Showing 15 plugins that match these filters.
zetetic-marketplacecdeust/zetetic-team-subagents1
task-pipelinessheleg/task-pipeline1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplace14 bundled product skills with 19 Python tools: product-skills fork-orchestrator with continuous-discovery loop (deterministic 16-lane router, Torres cadence tracker, OST linter, /cs-product + /cs-grill-product + /cs-product-loop), product manager toolkit (RICE, PRDs), product strategist, UX researcher, UI design system, competitive teardown, landing page generator, SaaS scaffolder, product analytics, experiment designer, product discovery, roadmap communicator, spec-to-repo, design-qa (UI finish gate: inert controls, missing states, rendered WCAG 2.2 checks). Companion standalone plugins: agile-product-owner, code-to-prd, apple-hig-expert, research-summarizer, design-qa.
Build, 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).
Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/autoresearch-agent:setup, /ar-run, /ar-loop, /ar-status, /ar-resume), 8 built-in evaluators, configurable loop intervals (10min to monthly).
A four-tier memory ladder for Claude Code where promotion is earned by recurrence, not asserted by confidence. L0 raw transcripts are never injected; L1 candidate atoms are gitignored and recalled on lexical relevance per prompt; L2 project context loads each session start; L3 stable persona is always loaded. L1 to L2 needs three distinct sessions spanning two distinct calendar days (a stated claim needs two; a verified claim is the only single-observation path); L2 to L3 needs two projects and thirty days. Two gates refuse rather than guess: a claim altered by the redaction pass never promotes on evidence alone, and a contradicted claim freezes until a human resolves it. Three hooks run the loop unattended and every one fails open. Nothing reaches a committed CLAUDE.md without an explicit human adopt. Ships 5 stdlib scripts, 3 hooks, a cs-memory-curator agent, /cs-memory, a JSON schema, and a 69-check validator. Concept from TencentCloud/TencentDB-Agent-Memory (MIT); no upstream code
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.
Skills, hooks, templates, and engineering guides for bootstrapping AI-agent-friendly projects, with a per-project self-improvement loop. Bundles the /new-project and /adopt-project scaffolding skills plus commit, simplify, reflect, remember, and dream.
scaffoldingComplete system: 15 problem-shaped skills backed by 97 genius agents, 86 skills total, 30 commands, 71 tools, 36 hooks, authoritative coding-standards rules, goal-driven and autonomous build loops, and the shared Claude Code and Codex gates
Runs a substantial task through a mandatory built-in intake grill, then 10 gated stages (docs, brainstorm+decompose, spec, plan, subagent build, tests, lint/deploy, post-deploy, docs/wiki, acceptance). Every stage's doctrine is built into the skill — no companion plugin required — with typed auto/judgment/manual gates, a frozen requirement spine that closes with evidence, a work board and a verification ledger that outlive a run, an exposure line naming what shipped unconfirmed, a progress rail computed from the project's own config, a proportional short path for small changes, a loop guard whose ceilings stop and record a blocker, and stage-3 tracks for what a product does, how it sounds and how it looks. Two modes need no task: `checkup` (what is unverified) and `setup` (audit existing docs); a third, `waves`, takes the whole board and closes it in waves that each finish in one pass. Retro insights can publish upstream as issues, opt-in and redacted.
development88 curated skills (incl. workspace-mode for cross-repo flows), 30 composite slash commands, 14 specialist subagents with per-agent model + reasoning-effort tuning, and 10 hook scripts that quietly enforce discipline (confirm-to-commit on protected branches, destructive-git gating, no AI-attribution trailers in commits/PRs, dependency pre-flight, iron rules injected at session start). Covers the whole SDLC — including post-PR: CI diagnosis, releases, dependency audits, live incident response. Drives the senior-IC loop end-to-end via /orc:flow — workspace-aware: from a parent dir with multiple sibling repos, one flow spans them all with N linked PRs.
An auditable, on-disk PDLC state machine for AI software engineering: a staged workflow (PRD → design → TDD → implement → review → ship → retro) with hard contracts + objective checks from real exit codes, so an autonomous loop can drive it to convergence unattended (fail-stop / budget guards) — tool-agnostic, richest in Claude Code, plus Codex via adapters.
workflowThe product-manager OS that gets better the more you use it: a CLAUDE.md operating brain, a memory that learns your product and team (3-min /setup), and a self-improving loop that watches the work you repeat and builds you custom skills for it. Plus 53 book-grounded skills across discovery → strategy → execution → launch — every one scored in CI and gated against regression — a workspace your artifacts land in, two isolated workers (critic + researcher), live connectors that write your work back to Linear/Notion/Slack, 5 chained workflows, ready-to-wire automations, and bundled getprompts + getskills libraries.
productivityDiscipline mode (staged planning, receipts, verify-against-source, adversarial review) + plan/kickoff commands + a plan-reviewer agent + an always-on SessionStart discipline injector + a Stop-hook autonomous loop (Layer 1, a deterministic gate) that can arm itself from a committed, content-hash-trusted .claude/tale-mode.json during a kickoff phase + a fail-closed plan-mode auto-approve for provably read-only shell (no more permission-dialog walls during investigation).
productivityZero-unverified-work execution harness: frozen specs, budgeted loops, hard gates, independent verification, honest terminal states.
Clears AI reviewer feedback on your PR: reads real review-thread state, sweeps the sibling instances the reviewer missed, gates every push on your repo's own tests, then requests re-review — hard-capped at 3 re-review requests. Claude Code, Codex, Gemini and Copilot built in; any reviewer bot can be configured.
code-reviewOptional companion to tale-mode: the read-only stuck-loop governor (Layer 2). Zero idle cost — a free bash gate escalates to ONE read-only model call (claude -p on Claude Code, sandboxed codex exec on Codex) exactly when a goal first fails twice, and returns an advisory finding. Install if you want anchor-breaking on stuck loops.
productivity
