Agent Plugins Marketplace

Recently added

Plugins grouped by the day they were added to the directory, newest first.

Sep 24, 2026

  1. The BFCM Support Kit: six tools for the customer service work outside a chat app. Readiness audit, sale terms and returns policy QA, per-zone delivery cutoffs, peak load and staff cover planning, a staff playbook with contingency plans, and a daily shipping exception watch. Independent of any inbox, chatbot or helpdesk.

    Claude CodeAgent Plugins6 skills
  2. chudarin4stars

    Five skills for agents that design in Figma, one per stage of the work: plan flows, audit a design system, design screens, write to the Plugin API without silent failures, repair detached variable bindings.

    Claude Code5 skills
  3. once0stars

    Execution safety for consequential external side effects across ambiguous retries, lost responses, idempotency gaps, reconciliation, and multi-agent handoffs. Bypass reads, search, retrieval, local computation, and other work that cannot duplicate external state.

    Codex1 skill1 MCP server
  4. Stop rewriting Claude Code's prompt cache by accident: a model-switch guard, a keep-alive tuned to your own breaks, and an audit of what each cache rebuild cost, on subscription usage or API prices.

    Claude Code1 skill
  5. Keep noisy command output (tests, builds, package managers, diffs, logs) out of the context window. Ships the lm-resizer skill and the lm-resizer MCP server (compress, tool_output, retrieve, stats). Requires the lm-resizer binary on PATH.

    Claude Code1 skill1 MCP server
  6. Persistent long-term memory for Claude Code: MCP tools for search/recall, a SessionStart hook that surfaces recent memories automatically, and /remember + /recall slash commands for direct CLI-backed writes and searches.

    Claude Code1 MCP server
  7. Register, run, inspect, integrate, and recover dagq tasks through the locally built dagq binary. Skills plus a SessionStart hook that re-orients a maintainer session; the queue database is never touched directly.

    Claude Code3 skills
  8. Graph-grounded codebase understanding and change-impact analysis for Codex.

    Codex3 skills1 MCP server
  9. Rust MCP server that indexes ANY codebase into a LadybugDB property graph — source in 11 languages with full AST, plus docs/config/binaries as File nodes (.js→Imports, Markdown→References). Resolves imports and call chains, detects communities via Leiden, traces execution flows from entry points, and exposes 26 MCP tools to agents — index_codebase, query_graph, get_symbol, get_impact, get_context, semantic_diff, and more.

    Claude Code3 skills1 MCP server
  10. 한글 문서(.hwp·.hwpx)나 그 문서가 든 .zip을 한컴 없이 읽는다. 본문·표(병합 셀, 다단 헤더, 표 안의 표)·숨은 메모·변경추적을 보존해 마크다운으로 뽑는다. 의존성 0, 읽기 전용.

    Claude Code1 skill
  11. readwise1stars

    Readwise ingestion for the vault contract, as scripts the pipeline runs: Reader/Classic highlights into origin-prefixed 01_Capture/ notes with their provenance.

    Claude Code
  12. radar1stars

    Active research radar: judges every Reader feed item against your interests with typed judgments, reports which feeds earn their place, proposes new feeds, and asks Kagi (search, news, answers, summaries).

    Claude Code1 skill
  13. obsidian1stars

    Vault interface: filesystem-first operations and health, search, graph-aware distill, and the unattended pipeline that rebuilds Index, maps and Now.

    Claude Code3 skills
  14. memory1stars

    Session-end capture and on-demand distillation into vault memory: archives session records to 00_Memory/sessions/ via a hook, then distills durable notes to 00_Memory/notes/ via a two-phase-review skill.

    Claude Code1 skill
  15. handoff1stars

    Portable session handoff: save/resume work context across sessions, machines, and tools via chained in-repo _handoff/ markdown, with a vault discovery index and PreCompact safety net.

    Claude Code1 skill
  16. Jev-powered verbatim compaction: once context reaches 60%, prunes stale tool calls with zero generation. Skips (never falls back to the LLM summarizer) when nothing is prunable; records evidence for learning.db.

    Claude Code
  17. Bundled Third-Party Suite - Curated external skills (Anthropic, RooCode, Community)

    Claude Code12 skills
  18. Keycloak 26.x extension (provider JAR) development - SPI catalog grounded in the target tag's source, Maven packaging and shading, Docker dev environment (start-dev, reverse proxy, two-node cluster), real verification, pitfalls, and turning a fork/PR into a plugin (keycloak-provider-dev)

    Claude Code1 skill
  19. Common Utilities Suite - Cross-platform development tools for Claude & Kilo (gitignore, markdown-formatter, macroplan-authoring, merge-resolver)

    Claude Code3 skills
  20. Angular v20+ Development Suite - authoring publishable libraries (own: angular-library), plus 10 vendored application-side references (component, di, directives, forms, http, routing, signals, ssr, testing, tooling) from analogjs/angular-skills (MIT, Brandon Roberts) - see README.md for which is which

    Claude Code10 skills
  21. Kilo/Claude ecosystem meta-tooling - plugin management from git marketplaces, scope management, agent alignment across the two hosts, RAG index maintenance, configuration authoring, framework-to-skillset generation

    Claude Code3 skills
  22. Bounded, value-aligned self-improvement workflows (ESRA) for Claude Code: five on-demand skills plus a dependency-free local runtime for evidence logs, baselines, experiments, audits, and human-reviewed oversight proposals.

    Claude Code5 skills
  23. plumlayer0stars

    Connect your agent to your Plumlayer project record and the precon skills that work it: upload and index drawing sets, build one cited scope list for the job and split it into trade packages, level sub bids, and place takeoffs. Everything recorded carries its author, the time, and the sheet it came from.

    CodexClaude Code8 skills1 MCP server
  24. Set up agent-starter in any project for Claude Code (.claude/) or Antigravity (.agents/). Deep-scans the codebase, interviews you, then installs and customizes only the config the project actually needs.

    Claude Code3 skills
  25. As três skills que trabalham juntas: /faz leva um pedido até código verificado encadeando o SDD/TDD do Matt Pocock, /obsidian-docs guarda o porquê num vault Obsidian fora do repositório, e /cpv fecha a leva no git e na documentação ao mesmo tempo. Traz o servidor MCP vault-docs e o agent vault-migrador.

    Claude Code3 skills1 MCP server
  26. wayfinder1stars

    Chart a multi-session effort as a labeled map of typed decision tickets (grilling / prototype / research / task) with explicit dependencies and an open frontier agents self-assign into. Plans; never executes.

    Claude Code1 skill
  27. voice1stars

    Route every response element to exactly one voice: prose to human-voice (verdict-first, confidence-tagged), machine-read artifacts to machine-voice (compressed traces, logs, status lines); plus ai-writing-mistakes, a wording pass that strips the tells marking prose as machine-written, and second-opinion, an offer-only subagent validation pipeline that never runs unbidden.

    Claude Code4 skills
  28. Never assert a fact, completion, or reproduction claim without naming and running the specific check that would prove it false, first.

    Claude Code1 skill
  29. Ship the thinnest end-to-end slice through a system first, then widen it in place — for both software delivery and open-ended investigation/research. Use when scoping new work, de-risking unknowns, or planning how to explore an unfamiliar problem before committing to a full build.

    Claude Code1 skill
  30. Set up and troubleshoot secretless GitHub Actions -> Tailscale auth via Workload Identity Federation (WIF): GitHub OIDC exchanged for short-lived Tailscale tokens, with no stored API keys or OAuth secrets.

    Claude Code1 skill
  31. stop-rule1stars

    A halting discipline for iterative fix loops: after a bounded number of failed attempts at the same objective, stop and report the state with hypotheses — never make attempt N+1 on momentum. Use when re-pushing to fix CI, retrying a flaky repro, or any loop where each retry is a guess rather than a diagnosis.

    Claude Code1 skill
  32. Classify a candidate action as PATCH/MINOR/MAJOR (semver-style blast-radius test) before acting — act silently on PATCH, flag-and-stage MINOR, stop for explicit human sign-off on MAJOR. Use whenever you're mid-task and unsure how much autonomy to take on the next action: which of several implementation paths to pick, whether to overwrite unreviewed state, whether to disable a safety toggle, or any judgment call settings.json's autoMode patterns don't enumerate.

    Claude Code1 skill
  33. Keep every hunk of the diff traceable to the stated task: anything discovered outside scope is recorded as a finding (ticket, note, diary entry) — never fixed in the same change. Use when starting any bounded task, when tempted to 'fix it while I'm here', or when reviewing whether a diff crept beyond its mandate.

    Claude Code1 skill
  34. redgate1stars

    Working harness for nontrivial work that needs explicit falsifiable criteria, verified ARM/TRACE/JUDGE rounds, or classified human gates. Compose around the most-specific specialist skill or recipe; Redgate reinforces execution and verification rather than replacing the domain procedure.

    Claude Code3 skills
  35. Close the growth loop's DETECT step: read the exhaust every run already sheds — stop-reports, scope-fence findings, unmet criteria, diary entries — cluster it by failure shape, and surface any shape seen at least N times as a named candidate invariant with its sightings cited. Proposes; never scaffolds. Use when asking what keeps going wrong, or before adding a skill on a hunch.

    Claude Code1 skill
  36. Rehearse the rollback before any irreversible action: name the specific restore path and demonstrate it works — never proceed on the strength of 'a backup exists'. Use before deletes, drops, force-pushes, migrations, or any action semver-gate classifies as MAJOR.

    Claude Code1 skill
  37. Scaffold a new marketplace plugin skeleton in one command: a deterministic generator emits a valid plugin.json, an invariant-first SKILL.md, cross-harness AGENTS.md symlinks, a command stub, and a red-by-default eval that fails closed until you implement real checks — then wires it into the marketplace lockfile.

    Claude Code1 skill
  38. Two reusable multi-agent orchestration templates for research-and-verify work on Claude Code's Workflow tool: fan out research over dimensions, then adversarially verify the claims that research surfaces so plausible-but-wrong findings don't survive. Ships a shared skill, two workflow-script templates (derived-verify, pipelined-verdict-wins), and a worked example.

    Claude Code1 skill
  39. grill-me1stars

    Interview the user about a plan before work starts, single-session and no subagents required, walking its design tree and scaling question depth to each branch's stakes (reversibility x blast radius) while offering a recommendation at almost every step. Use on phrases like grill me, interview me about this plan, stress-test this plan, or before starting a nontrivial multi-step change whose design isn't yet settled.

    Claude Code1 skill
  40. graveyard1stars

    Archive old GitHub repositories into a single private graveyard repo as restorable git bundles, then safely delete the originals. Captures full history (branches, tags, PR refs) and never deletes an original until its backup is verified.

    Claude Code1 skill
  41. Deploy daily GitHub automation that curates a living, self-invalidating operating index (a 'fleet playbook') for a glob of repos — always pointing at the repos as the source of truth, never posing as it.

    Claude Code1 skill
  42. Search for the existing implementation before writing a new one: name the searches you ran for an existing helper, abstraction, or pattern and what they returned, before introducing anything new. Use before adding a utility, wrapper, config knob, or dependency to a codebase you did not write end-to-end.

    Claude Code1 skill
  43. Design and audit an agent system's eval ladder — the cheapest rung that catches each regression, the blind spot beside every green, judges validated by TPR/TNR, pass^k for irreversible actions. Use when designing, auditing, or defending a test/eval strategy for an agent, skill, or prompt; when adding an eval tier or LLM judge; or when a suite is all-green and you cannot say what it would catch.

    Claude Code1 skill
  44. Before any call that transmits repo or user content off-machine (posting a comment, pushing a branch, calling an external API with file contents in the payload), state what is being sent and to whom — permission modes gate the call, this gates the content. Use whenever output leaves the machine to a destination the user didn't name in this task.

    Claude Code1 skill
  45. Audits CLAUDE.md/AGENTS.md/SKILL.md instruction files against current repo state, catches claims that have gone stale (a renamed path, a dropped command, a policy that changed) before they get trusted or acted on, and resolves contradictions between layered instruction files (root vs nested, SKILL.md vs its parent AGENTS.md) down to one explicit kept version instead of leaving both to stand. Use before trusting or propagating any instruction-file claim you haven't personally re-checked, whenever onboarding a repo's docs for the first time, right after a refactor/rename/policy change that could invalidate what's documented, or whenever two instruction files (or an instruction file and the actual repo) say different things about the same fact. Trigger phrases: 'audit the docs', 'is AGENTS.md still accurate', 'clean up CLAUDE.md', 'these instructions contradict each other', 'refactor the AGENTS.md files'.

    Claude Code1 skill
  46. Diagnose a bug by writing ranked, falsifiable hypotheses before any code change, tagging temporary debug instrumentation for a zero-tolerance sweep, and gating the regression test to a red-then-green proof at the confirmed seam. Use when fixing a bug, debugging a failure, triaging an error, or the user asks to diagnose/root-cause/troubleshoot an issue.

    Claude Code1 skill
  47. dev-diary1stars

    Keep a scannable developer journal that writes itself: discover a day's work from local Claude Code sessions, git commits, and prompt history; interview the user about what mattered and why; and record a tight, dated entry. Ships /dev-diary (write today) and /dev-diary-review (revise a past day). The journal is a separate private repo; this plugin is just the tool.

    Claude Code2 skills
  48. Walk the ordered continue, clear, handoff, delegate, compact decision tree at a phase boundary, and keep any handoff artifact pointer-only — settled specs, plans, ADRs, issues, commits, and diffs referenced by path or URL, never copied inline. Use this when the context window is getting full, you're wondering whether to clear or compact, you need to hand off to another harness, directory, or colleague, you've hit a phase boundary and aren't sure whether to keep going or start fresh, or you want to cache hard-won research before it's lost.

    Claude Code1 skill
  49. Before writing a new interface (module boundary, class API, function signature, or service contract) that at least two call sites will depend on, that crosses a module/service/team/persistence boundary, or that will be expensive to change later — produce 3+ radically different candidate designs and compare them on depth, locality, and seam placement before picking one. Use on "before committing to an interface", "design this API/module/class boundary", "how should this be structured", "compare interface designs", "is this the right abstraction", "design it twice", reviewing a proposed interface shape in a PR — or self-trigger whenever about to write a new interface meeting that bar.

    Claude Code1 skill
  50. Compile deterministic, content-hashed agents from small behavior modules: a skill turns fuzzy intent into a typed AgentQuery, a stdlib-only kernel resolves modules, expands dependencies, fails closed on conflicts and over-ceiling effects, and emits an immutable AgentImage plus a rendered harness-native subagent — never inventing behavior text without provenance.

    Claude Code1 skill1 MCP server