19 плагинов из публичных маркетплейсов Claude Code. Каждый объединяет навыки, слэш-команды, агентов, хуки или MCP server, которые устанавливаются вместе.
Показано 19 плагинов, соответствующих фильтрам.
obsidian-second-braineugeniughelbur/obsidian-second-brain1
claude-code-workflowswshobson/agents1
cortex-pluginscdeust/Cortex1
wasp-nestlegioncodeinc/vibe-coding-tools1Отправьте репозиторий с .claude-plugin/marketplace.json, и мы перечислим каждый плагин.
Отправить marketplaceStop re-explaining your notes to Claude. Turns your Obsidian vault into memory Claude can actually search, and keeps it true: new sources rewrite existing pages, contradictions reconcile, and stale facts get flagged. AI note-taking and PKM for Claude Code.
NVIDIA DGX Spark (GB10) environment operations. Use when setting up, preflighting, or debugging ML workloads on DGX Spark or aarch64 Blackwell hardware — CUDA-13 wheel/ABI checks, unified-memory OOM ladders, thermal monitoring.
Study companion for the Deep Learning textbook by Goodfellow, Bengio & Courville (MIT Press, 2016), free to read at deeplearningbook.org. Twenty chapter files, a glossary, patterns and a cheatsheet index the whole book, and a delta reference dates it against 2026 practice with per-claim confidence levels: double descent qualifying the U-curve, AdamW splitting weight decay from L2, transformers displacing Chapter 10's recurrence, diffusion growing out of Chapter 18's score matching. Four stdlib tools make it executable — a prerequisite-closed reading-path planner that refuses goals the book does not cover, a training diagnostic running Chapter 11's rules in priority order so a NaN is never reported as overfitting, a capacity planner that ranks 'shrink the model' last when overparameterized, and a parameter/FLOP/activation-memory calculator that refuses a stack whose shapes do not connect. A companion, not a compilation: the book is copyrighted, so nothing here reproduces its text.
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.
Engineer an agent's forgetting, not just its remembering. Four deterministic stdlib scripts implement the four lenses of agent memory: a cost profiler that splits construction from query spend and reports cost per correct answer (construction energy exceeds total query energy across 300 queries in the Stanford characterization); an architecture picker that scores the four paradigm families — long-context, flat RAG, structure-augmented RAG, agentic — disqualifies on hard constraints, names the cost the winning choice makes you pay, and refuses to pick when the top two tie; a density auditor that classifies every record in a memory directory or JSONL export as FACT / SKILL / LOG / PROSE, finds near-duplicates, and flags stale wording; and a forgetting-policy linter that fails any design with no forgetting rule. Ships cs-memory-engineer agent, /cs-memory-engineering and /cs-forgetting-audit commands, 4 references, and a seven-question forcing worksheet.
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
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).
Persistent memory plugin for Claude Code - remembers preferences, decisions, and corrections across sessions and context limits
Cortex — persistent memory and cognitive profiling for Claude Code (renamed from the 'cortex' plugin in v4.15.0 to match the PyPI/MCP-registry identity hypermnesia-mcp) — thermodynamic memory with heat/decay, intent-aware retrieval, biological plasticity, codebase intelligence, and cognitive profiling. These mechanisms are implemented and inspectable; committed ablations do not establish a retrieval gain from all 36 mechanisms. 57 MCP tools (60 with the optional ai-architect-mcp-codebase + ai-architect-mcp-spec integrations) with enriched schemas (visualization extracted to the standalone Hypermnesia MCP Viz server). PostgreSQL + pgvector in CLI mode; automatic SQLite fallback in Cowork/sandboxed mode. v3.17.0 — autonomous per-project wiki: SessionStart auto-spawns a 6-hour consolidate cycle; a headless `claude -p` worker drains the curation-gap queue, calls codebase-intelligence MCP tools to ground each section in the real call graph, and authors missing anchor pages (architecture / s
Profile application performance with CPU, memory, and execution time analysis
Turn Littlebird memory into evidence-backed operating work.
Graph-backed memory and context optimization workflows with graphify first and document conversion helpers second.
developer toolsDetect memory leaks and analyze memory usage patterns
Shared debug memory and verified dynamic Skills for Claude Code agents.
Memory-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.
The 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.
productivityLocal-first recall, strict agent-mediated automatic capture, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.
workflow orchestrationMultimodal RAG, video search, image similarity search, agent memory, and embeddings stored with your data. Tables, computed columns, vector search, and video, audio, image, and document pipelines.
A portable GTD skill for Claude Code: capture / clarify / organize / engage / review over plain-Markdown lists in memory/gtd/. The bundled skill auto-activates; /gtd and /gtd-* commands are included. Calendar writes are confirmation-gated and fail-closed.
