공개 Claude Code 마켓플레이스의 플러그인 25개입니다. 각 플러그인은 함께 설치되는 스킬, 슬래시 명령, 에이전트, 훅 또는 MCP 서버를 묶습니다.
필터와 일치하는 25개의 플러그인을 표시합니다.
.claude-plugin/marketplace.json이 포함된 repo를 제출하면 모든 plugin을 목록에 추가합니다.
marketplace 제출Internal BizOps domain. v2.8.0 ships 7 skills: orchestrator + process-mapper (BPMN/bottleneck/cycle-time, Lean+TOC) + vendor-management (scorecard+SLA+3rd-party risk, NIST SP 800-161/ISO 27036) + capacity-planner (Erlang-C queueing math for ops teams, NOT engineering) + internal-comms (ADKAR+Kotter 8-step, NOT marketing) + knowledge-ops (SOP+runbook+KB hygiene with 5W2H, context: fork) + procurement-optimizer (UNSPSC spend categorization + supplier consolidation). Orchestrator uses context: fork to route inquiries via Matt Pocock grill discipline (one question per turn, recommended answer, canon-cited challenge). Every SKILL.md ships a Forcing-question library section. 18 stdlib Python tools, 24+ reference docs. Distinct from business-growth (external sales) and c-level-advisor (strategic).
Per-deal-and-packaging Commercial domain. v2.8.0 ships 8 skills: orchestrator + pricing-strategist (model picker + Van Westendorp WTP + packaging) + deal-desk (deal scorer + discount approval routing + redline) + partnerships-architect (5-tier classifier + joint GTM + revshare modeler) + channel-economics (cost-to-serve + ROI + mix optimizer) + commercial-policy (data-backed discount matrix + exception flow + linter) + rfp-responder (Shipley structured RFP/RFI/RFQ + win-theme + winrate predictor, context: fork) + commercial-forecaster (4Q-weighted bookings + cohort NRR/GRR + funnel-confidence with mandatory assumption disclosure). Hard rules: pricing outputs model+range (never a single number), deal outputs route to named human approver (never auto-approve), forecast outputs surface conversion assumption, RFP never invents claims for GAP requirements. 21 stdlib Python tools, 28+ reference docs. Distinct from business-growth (sales execution), c-level-advisor/cro-advisor (strategic), fi
Enterprise / cross-functional Research Operations domain — the managed counterpart to the academic research/ domain. v2.9.0 ships 5 skills: orchestrator (context: fork), clinical-research (protocol synopsis, endpoint selection, sample-size/power for means/proportions/survival, phase-gate feasibility), research-finance (R&D budgeting with F&A split, burn/runway, capitalize-vs-expense routing, portfolio ROI), market-research (TAM/SAM/SOM top-down and bottoms-up, survey sampling with FPC, Kotler segmentation), and product-research (goal-matched study design, method-based saturation, insight synthesis flagging single-source anecdotes). Hard rules: outputs are estimates routed to a named clinical or finance owner, market sizes show method + assumptions, product insights require recurrence across independent participants. 24 stdlib Python tools, 12 reference docs. Distinct from ra-qm-team, finance, research/grants, product-team, and marketing-skill.
A second brain for Claude Code + Obsidian inspired by Karpathy's LLM Wiki gist. Turn any LLM CLI into a disciplined wiki maintainer: incrementally ingest sources into a persistent, interlinked markdown vault; update entity/concept/source pages; flag contradictions; maintain index and append-only log. Knowledge compounds instead of being re-derived by RAG on every query. Ships 3 sub-agents (wiki-ingestor, wiki-librarian, wiki-linter), 5 slash commands (/wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log), 8 Python tools (stdlib only: init_vault, ingest_source, update_index, append_log, wiki_search BM25, lint_wiki, graph_analyzer, export_marp), 8 reference docs, full vault templates (CLAUDE.md, AGENTS.md, cursorrules, 5 page templates), and a worked example vault. Cross-tool compatible with Claude Code, Codex CLI, Cursor, Antigravity, OpenCode, and Gemini CLI.
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.
Gate a UI before it is called done: check the build, not the design file. Three deterministic stdlib scripts: a finish linter that blocks on controls that do nothing, dead links, placeholder copy and removed focus rings, and warns on template defaults; an interaction-state checker that derives loading, empty, error, busy and focus states from each surface's kind and blocks when they are missing or unevidenced; and a rendered audit that reads a browser snapshot and blocks on WCAG 2.2 AA failures in contrast, focus visibility, focus obscured, reflow at 320 px, accessible names and target size. Ships a read-only snapshot collector, an optional Playwright keyboard pass, cs-design-qa agent, /cs-design-qa and /cs-ui-finish-lint commands, 3 cited references and a finish sign-off.
Converts books, documentation folders, and source collections (PDF, EPUB, DOCX, HTML, Markdown, RST, AsciiDoc, RTF, MOBI/AZW) into structured agent skills: a master SKILL.md with core frameworks and a topic index, on-demand chapter files, a glossary, a patterns file, and a decision cheatsheet. Ships 4 stdlib-only tools (multi-format extractor with invisible-Unicode sanitization, four-family generated-skill validator covering frontmatter/safety/budget/index, pre- and post-flight token budget estimator with a worth-converting verdict, and a plugin emitter that wraps a compiled skill as an installable claude-skills package behind a rights gate), 5 references citing 7-8 sources each, a cs-book-to-skill agent, and /cs-book-to-skill + /cs-book-to-plugin commands. Derived from virgiliojr94/book-to-skill (MIT).
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.
Prove your user access reviews before the auditor tests them. Three deterministic stdlib scripts: a roster diff that joins the HR roster to account exports and blocks on leavers still enabled or used after exit, privileged orphans and ownerless privileged service accounts; a campaign checker that blocks on population gaps, undecided lines, self-review and revokes not removed inside your window, and flags rubber-stamping; and a control mapper that turns findings into per-control status for SOC 2, ISO 27001, NIST 800-53, PCI DSS, HIPAA and SOX IPE. Ships cs-access-reviewer agent, /cs-access-review and /cs-access-diff commands, 3 cited references and an access review sign-off template.
Get a defense supplier ready for a CMMC 2.0 Level 2 assessment. Three deterministic stdlib scripts: an SPRS scorer that weights all 110 NIST SP 800-171 Rev 2 requirements per 32 CFR 170.24 and blocks gaps that can never go on a POA&M; a POA&M closeout tracker that checks every deferred gap against the 180-day Conditional status deadline and the annual affirmation calendar; and a scope classifier that sorts the asset inventory into the 170.19 categories and blocks on assets missing from the SSP or cloud providers holding CUI without FedRAMP. Ships cs-cmmc-assessor agent, /cs-cmmc-readiness and /cs-sprs-score commands, 3 cited references and a readiness sign-off.
Get products ready for the EU Cyber Resilience Act (Regulation 2024/2847). Four deterministic stdlib scripts: a scope classifier that sorts a portfolio into default, important class I/II and critical (Annex III/IV), blocks conformity routes Article 32 does not allow, checks support periods and names the CSIRT for Article 14 reports; an Article 14 clock for the 24h/72h/14-day/one-month deadlines live since 11 September 2026; an Annex I/II/VII gap check before the EU declaration of conformity; and an SBOM floor check for CycloneDX and SPDX. Ships cs-cra-officer agent, /cs-cra-readiness and /cs-cra-report commands, 3 cited references and an Article 14 runbook.
Get medical device software through IEC 62304 and IEC 81001-5-1. Four deterministic stdlib scripts: a software safety classifier (62304 4.3 with A1 external controls and segregation) that also sets the FDA Basic/Enhanced documentation level and flags 524B cyber devices; a lifecycle gap check scoped by class, with IEC 81001-5-1 security activities; a SOUP register check with SBOM cross-check; and a trace matrix release gate. Ships cs-device-software-lead agent, /cs-medical-device-software and /cs-soup-review commands and 4 references with per-claim confidence levels.
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
Prove an agent, prompt, model or tool change did not make the agent worse. Three deterministic stdlib scripts: a trajectory checker that grades tool-call paths (strict / unordered / subset / superset match modes, argument matching, forbidden tools that block in every mode, call ceilings); a flake detector that classifies each case as stable or flaky from repeated trials and reports pass@k and pass^k with Wilson intervals; and a paired regression gate that averages trials per case, tests per-case differences with a t-based CI and an exact one-sided McNemar test, and blocks the merge on a significant drop, a critical-case regression, a dropped case, or a quarantine entry without owner and expiry. Ships cs-eval-gatekeeper agent, /cs-agent-evals and /cs-eval-gate commands, 3 references, and a CI job example.
Ship a new language without the usual breakage. Three deterministic stdlib scripts: a translation-file checker for JSON/ARB (i18next, ICU), .properties, .strings, Android strings.xml and gettext .po that blocks on missing keys, renamed placeholders, ICU syntax errors, plural/select without other, zero branches that never match and plural categories the target locale needs, from the embedded Unicode CLDR 49 table (ru few/many, ar six forms); a hardcoded-string scanner for React, Vue, Svelte and HTML that flags text and user-facing attributes outside t(), concatenated translations, locale-less toLocaleString and '$' + amount; and a pseudo-locale generator (en-XA accented and expanded, ar-XB right-to-left) that keeps placeholders and ICU syntax intact. Ships cs-i18n-engineer agent, /cs-i18n-check and /cs-pseudo-locale commands and 3 cited references.
Turn a tangled working tree into a clean, reviewable commit series. Three deterministic stdlib scripts over git: a series planner that groups changes into commits in build-safe order (manifest with lockfile, pure moves, formatting, each module's change with its tests, docs, CI), holds back .env and key files, and flags mixed formatting and moves whose callers would break; a secret gate that scans staged or pushed lines for provider tokens, high-entropy secrets, sensitive files and conflict markers and blocks before the commit exists, with redacted output and reasoned waivers; and a message linter that blocks vague subjects, missing why on large changes and pending fixup commits, matching the repo's own convention. Ships pre-commit, commit-msg and pre-push hooks, cs-commit-craft agent, /cs-commit-craft and /cs-commit-check commands and 3 cited references.
Roll Claude Code out to a team with guardrails you can check. Four deterministic stdlib scripts: a settings linter that reads shared, local, user and managed settings together (array merge, deny-ask-allow order) and blocks blanket shell allows, pre-approved destructive commands and committed credentials; an MCP and plugin inventory that blocks anything missing from your approved list or holding a literal secret, and flags unpinned or plain-http servers; a CLAUDE.md layering audit that resolves every layer and @import and flags broken imports, contradictions, secrets and resident size; and a privacy-safe adoption tracker that turns local session files into counts only and classifies the rollout as PILOT, SPREADING, EMBEDDED or STALLED. Ships cs-claude-code-rollout agent, /cs-claude-rollout and /cs-claude-settings-lint commands, 3 references, a baseline managed-settings policy and a four-phase rollout plan.
Run a faster, provable month-end close. Three deterministic stdlib scripts: a close calendar planner that orders tasks by dependency, finds the critical path and slack, maps WD+n deadlines to dates and blocks on missing owners, missing or self-review of key controls and a critical path past the target workday; a reconciliation matcher that matches GL to bank or sub-ledger by reference then amount and date, builds the proof, ages reconciling items and blocks on any unexplained difference or preparer-as-reviewer; and a flux analyzer that applies your materiality rule and refuses material fluctuations explained with boilerplate or without a quantified driver. Ships cs-close-controller agent, /cs-month-end-close and /cs-flux-review commands, 3 references citing COSO 2013 and PCAOB AS 2201 / AS 2305 / SAPA 11, and a reconciliation sign-off template.
Active coding discipline enforcer based on Karpathy's 4 principles: surface assumptions, simplify, make surgical changes, define verifiable goals. Ships 4 Python tools (complexity_checker, diff_surgeon, assumption_linter, goal_verifier), a review agent, /karpathy-check command, and pre-commit hook. All stdlib-only.
Workflow-builder skill: design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool (CLAUDE_CODE_WORKFLOWS=1, /workflows). Every session opens with an intake question set; when the user is vague, a stdlib recommendation engine infers and proposes a topology with rationale instead of stalling. Ships 3 stdlib Python tools (intake recommendation engine, .js validator enforcing pure-literal-meta / no-non-determinism / guarded-loop / parallel-thunk rules, topology scaffolder), 3 references citing 7-8 authoritative sources each (API surface, orchestration patterns, decision + intake guide), templates + a runnable example, cs-workflow-architect persona agent + /cs-workflow-build slash command. Use when building, scaffolding, or running a custom Claude Code workflow or orchestrating sub-agents (fan-out, pipeline, loop, judge-panel).
