9 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
sdlc-graph-engineeringRonMizrahi/ai-sdlc-graph1
shut-up-and-codechl03ks/shut-up-and-code1Submit the repo with .claude-plugin/marketplace.json and we list every plugin.
Submit marketplace32 engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright (9 sub-skills), self-improving agent, Stripe integration, TDD guide, tech stack evaluator, Google Workspace CLI, a11y audit (WCAG 2.2), Azure cloud architect, GCP cloud architect, security pen testing, Snowflake development, adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection. v2.8.1 audits senior-fullstack / senior-frontend / senior-backend against karpathy-coder + Matt Pocock — each ships a 7-question forcing-question library, 4 customization profiles (JSON), deterministic decision engine, composition map into POWERFUL specialists, plus cs-fullstack-engineer / cs-frontend-engineer / cs-backend-engineer orchestrator agents (context: fork) + /cs-fullstack-review, /cs-frontend-review, /cs-backend-review, /cs-engineer-grill slash commands.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract patterns into skills. Ships 5 slash commands (/si:memory-review, /si:promote, /si:extract, /si:memory-status, /si:remember) and 2 sub-agents (memory-analyst, skill-extractor).
Answer questions about past agent runs from the recording, not from memory. Three read-only stdlib scripts over the session transcripts Claude Code and Codex already write: a finder that locates the run by repo, time window, touched file or command text; a timeline that numbers every step with its exit code, lists every file changed (flagging changes the agent never mentioned) and walks back from any step with each causal edge labelled recorded or inferred by a named rule; and a claim checker that tests a summary's claims (ran, passed, edited, not-edited, read) against the run and catches tests that passed before a later edit and exit codes that belong to the last command of a pipe. Secrets are always redacted. A UserPromptSubmit hook gives the agent this session's transcript path when a prompt asks about past work. Ships cs-run-forensics agent, /cs-run-forensics and /cs-check-claims commands and 3 cited references.
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
Your 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).
AI agents say "done" too easily. dreamteam makes a second, independent agent prove it before anything ships, re-running your tests and rejecting fake or over-claimed passes.
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.
developmentThe SDLC as a guarded graph, with the milestone loop delegated to a milestone agent per milestone (per worktree under strategy C) whose bundle the orchestrator verifies against git before recording it. A run is one gitignored directory — state, per-milestone journals, and with --trace every state it passed through. Ships a run reviewer that turns a finished run into the evals it should have had, and an advisory onboarding skill that reports which third-party tools this session can invoke and what a run does without each. Command-invoked.
workflowComment discipline for Claude Code: a comment ships only if deleting it costs the reader something.
productivity
