Skip to content
Back to search

2389-research

SkillWorks with Claude CodeGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/2389-research--claude-plugins/badge.svg)](/listings/2389-research--claude-plugins)

HTML

<a href="/listings/2389-research--claude-plugins"><img src="/api/listings/2389-research--claude-plugins/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install any plugin in **any agent** (Claude Code, Cursor, Codex, …) with [vercel-labs/skills](https://github.com/vercel-labs/skills):

npx skills add 2389-research/simmer

Or natively in Claude Code:

# Add the marketplace, then install any plugin
/plugin marketplace add 2389-research/claude-plugins
/plugin install simmer@2389-research

> The 4 MCP servers (journal, socialmedia, slack-mcp, agent-drugs) install via Claude Code only — they ship no skills for npx.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 728 lines
  1. {
  2. "name": "2389-research",
  3. "owner": {
  4. "name": "2389 Research Inc",
  5. "email": "hello@2389.ai",
  6. "url": "https://2389.ai"
  7. },
  8. "metadata": {
  9. "description": "Plugins and MCP servers we use at 2389",
  10. "version": "2.0.0"
  11. },
  12. "plugins": [
  13. {
  14. "name": "css-development",
  15. "category": "development",
  16. "source": {
  17. "source": "url",
  18. "url": "https://github.com/2389-research/css-development.git"
  19. },
  20. "description": "CSS development workflows with Tailwind composition, semantic naming, and dark mode by default",
  21. "version": "1.0.0",
  22. "keywords": [
  23. "css",
  24. "tailwind",
  25. "styling",
  26. "components",
  27. "dark-mode"
  28. ],
  29. "strict": false
  30. },
  31. {
  32. "name": "firebase-development",
  33. "category": "infrastructure",
  34. "source": {
  35. "source": "url",
  36. "url": "https://github.com/2389-research/firebase-development.git"
  37. },
  38. "description": "Firebase project workflows including setup, features, debugging, and validation",
  39. "version": "1.0.0",
  40. "keywords": [
  41. "firebase",
  42. "firestore",
  43. "cloud-functions",
  44. "hosting",
  45. "emulator"
  46. ],
  47. "strict": false
  48. },
  49. {
  50. "name": "landing-page-design",
  51. "category": "development",
  52. "source": {
  53. "source": "url",
  54. "url": "https://github.com/2389-research/landing-page-design.git"
  55. },
  56. "description": "Create high-converting, visually distinctive landing pages with Vibe Discovery process and anti-AI-slop principles",
  57. "version": "1.0.0",
  58. "keywords": [
  59. "landing-page",
  60. "marketing",
  61. "design",
  62. "conversion",
  63. "hero",
  64. "saas",
  65. "homepage"
  66. ],
  67. "strict": false
  68. },
  69. {
  70. "name": "xtool",
  71. "category": "development",
  72. "source": {
  73. "source": "url",
  74. "url": "https://github.com/2389-research/xtool.git"
  75. },
  76. "description": "Xcode-free iOS development with xtool - build SwiftPM apps on Linux, Windows, and macOS without Xcode",
  77. "version": "1.0.0",
  78. "keywords": [
  79. "ios",
  80. "xtool",
  81. "swiftpm",
  82. "swift",
  83. "xcode-free",
  84. "cross-platform",
  85. "widgets",
  86. "extensions"
  87. ],
  88. "strict": false
  89. },
  90. {
  91. "name": "building-multiagent-systems",
  92. "category": "agents",
  93. "source": {
  94. "source": "url",
  95. "url": "https://github.com/2389-research/building-multiagent-systems.git"
  96. },
  97. "description": "Architecture patterns for multi-agent systems with orchestrators, sub-agents, and tool coordination",
  98. "version": "1.0.0",
  99. "keywords": [
  100. "multi-agent",
  101. "orchestrator",
  102. "coordination",
  103. "agents",
  104. "architecture",
  105. "patterns"
  106. ],
  107. "strict": false
  108. },
  109. {
  110. "name": "speed-run",
  111. "category": "development",
  112. "source": {
  113. "source": "url",
  114. "url": "https://github.com/2389-research/speed-run.git"
  115. },
  116. "description": "Token-efficient code generation pipeline - parallel implementation with hosted LLM (Cerebras) for ~60% token savings. Includes MCP server.",
  117. "version": "1.1.1",
  118. "keywords": [
  119. "codegen",
  120. "speed-run",
  121. "parallel",
  122. "hosted-llm",
  123. "cerebras",
  124. "token-efficient",
  125. "turbo",
  126. "race",
  127. "mcp"
  128. ],
  129. "strict": false
  130. },
  131. {
  132. "name": "test-kitchen",
  133. "category": "testing",
  134. "source": {
  135. "source": "url",
  136. "url": "https://github.com/2389-research/test-kitchen.git"
  137. },
  138. "description": "Parallel exploration of implementation approaches - implements multiple variants simultaneously and lets tests determine the winner",
  139. "version": "1.0.0",
  140. "keywords": [
  141. "parallel",
  142. "exploration",
  143. "variants",
  144. "comparison",
  145. "implementation",
  146. "testing",
  147. "worktrees"
  148. ],
  149. "strict": false
  150. },
  151. {
  152. "name": "simmer",
  153. "category": "testing",
  154. "source": {
  155. "source": "url",
  156. "url": "https://github.com/2389-research/simmer.git"
  157. },
  158. "description": "Iterative artifact refinement with investigation-first judge board - constructs problem-specific judges that read the code, understand the problem, and propose evidence-based improvements",
  159. "version": "3.0.1",
  160. "keywords": [
  161. "refinement",
  162. "iteration",
  163. "criteria",
  164. "scoring",
  165. "judge",
  166. "generator",
  167. "artifact",
  168. "improvement",
  169. "workspace",
  170. "evaluator",
  171. "pipeline",
  172. "optimization"
  173. ],
  174. "strict": false
  175. },
  176. {
  177. "name": "scenario-testing",
  178. "category": "testing",
  179. "source": {
  180. "source": "url",
  181. "url": "https://github.com/2389-research/scenario-testing.git"
  182. },
  183. "description": "End-to-end testing with real dependencies - no mocks allowed; scenarios with real data are the only source of truth",
  184. "version": "1.0.0",
  185. "keywords": [
  186. "testing",
  187. "e2e",
  188. "scenarios",
  189. "no-mocks",
  190. "integration"
  191. ],
  192. "strict": false
  193. },
  194. {
  195. "name": "fresh-eyes-review",
  196. "category": "testing",
  197. "source": {
  198. "source": "url",
  199. "url": "https://github.com/2389-research/fresh-eyes-review.git"
  200. },
  201. "description": "Mandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests",
  202. "version": "1.0.0",
  203. "keywords": [
  204. "review",
  205. "quality",
  206. "security",
  207. "commit",
  208. "pr",
  209. "bugs"
  210. ],
  211. "strict": false
  212. },
  213. {
  214. "name": "documentation-audit",
  215. "category": "testing",
  216. "source": {
  217. "source": "url",
  218. "url": "https://github.com/2389-research/documentation-audit.git"
  219. },
  220. "description": "Verify documentation claims against codebase reality - two-pass extraction with pattern expansion for comprehensive drift detection",
  221. "version": "2.0.1",
  222. "keywords": [
  223. "documentation",
  224. "audit",
  225. "verify",
  226. "drift",
  227. "accuracy",
  228. "claims",
  229. "markdown",
  230. "docs"
  231. ],
  232. "strict": false
  233. },
  234. {
  235. "name": "sift",
  236. "category": "testing",
  237. "source": {
  238. "source": "url",
  239. "url": "https://github.com/2389-research/sift.git"
  240. },
  241. "description": "Read-only whole-codebase audit for material simplifications in structure, state, control flow, algorithms, lifecycle, and ownership boundaries",
  242. "version": "1.2.0",
  243. "keywords": [
  244. "audit",
  245. "simplification",
  246. "refactoring",
  247. "complexity",
  248. "technical-debt",
  249. "codebase"
  250. ],
  251. "strict": false
  252. },
  253. {
  254. "name": "trace",
  255. "category": "testing",
  256. "source": {
  257. "source": "url",
  258. "url": "https://github.com/2389-research/trace.git"
  259. },
  260. "description": "Verify a repository against its authoritative spec with a canonical behavior matrix and executable evidence",
  261. "version": "0.2.0",
  262. "keywords": [
  263. "verification",
  264. "requirements",
  265. "spec",
  266. "acceptance-testing",
  267. "behavior",
  268. "audit"
  269. ],
  270. "strict": false
  271. },
  272. {
  273. "name": "ceo-personal-os",
  274. "category": "strategy",
  275. "source": {
  276. "source": "url",
  277. "url": "https://github.com/2389-research/ceo-personal-os.git"
  278. },
  279. "description": "Personal operating system for executives - reflection frameworks, goal systems, coaching-style reviews (Gustin, Ferriss, Robbins, Lieberman, Campbell, Eisenmann, Collins, Martell, Gerber, Blank)",
  280. "version": "1.0.0",
  281. "keywords": [
  282. "ceo",
  283. "executive",
  284. "reflection",
  285. "goals",
  286. "annual-review",
  287. "coaching",
  288. "campbell",
  289. "trillion-dollar-coach",
  290. "people-first",
  291. "eisenmann",
  292. "startup-failure",
  293. "why-startups-fail",
  294. "collins",
  295. "good-to-great",
  296. "level-5-leadership",
  297. "hedgehog-concept",
  298. "flywheel",
  299. "martell",
  300. "buyback-time",
  301. "delegation",
  302. "gerber",
  303. "emyth",
  304. "work-on-business",
  305. "franchise-prototype",
  306. "blank",
  307. "steve-blank",
  308. "customer-development",
  309. "lean-startup",
  310. "mvp",
  311. "pivot",
  312. "product-market-fit",
  313. "get-out-of-the-building"
  314. ],
  315. "strict": false
  316. },
  317. {
  318. "name": "worldview-synthesis",
  319. "category": "strategy",
  320. "source": {
  321. "source": "url",
  322. "url": "https://github.com/2389-research/worldview-synthesis.git"
  323. },
  324. "description": "Systematic worldview articulation - surface beliefs, identify tensions, generate narrative outputs for personal philosophy documentation",
  325. "version": "1.0.0",
  326. "keywords": [
  327. "worldview",
  328. "values",
  329. "philosophy",
  330. "beliefs",
  331. "manifesto",
  332. "mission",
  333. "self-discovery"
  334. ],
  335. "strict": false
  336. },
  337. {
  338. "name": "deliberation",
  339. "category": "strategy",
  340. "source": {
  341. "source": "url",
  342. "url": "https://github.com/2389-research/deliberation.git"
  343. },
  344. "description": "Decision-making through deliberation - seeking unity through discernment rather than consensus through debate",
  345. "version": "1.0.0",
  346. "keywords": [
  347. "decision-making",
  348. "discernment",
  349. "deliberation",
  350. "unity",
  351. "consensus",
  352. "ethics",
  353. "multi-agent",
  354. "clearness-committee"
  355. ],
  356. "strict": false
  357. },
  358. {
  359. "name": "terminal-title",
  360. "category": "infrastructure",
  361. "source": {
  362. "source": "url",
  363. "url": "https://github.com/2389-research/terminal-title.git"
  364. },
  365. "description": "Automatically updates terminal title with emoji + project + topic context for quick visual cues when switching terminals",
  366. "version": "1.1.2",
  367. "keywords": [
  368. "terminal",
  369. "title",
  370. "session",
  371. "context",
  372. "emoji"
  373. ],
  374. "strict": false
  375. },
  376. {
  377. "name": "slack-mcp",
  378. "category": "infrastructure",
  379. "source": {
  380. "source": "url",
  381. "url": "https://github.com/2389-research/slack-mcp.git"
  382. },
  383. "description": "Slack workspace integration MCP server - create channels, invite users, post messages, manage threads for team collaboration",
  384. "version": "1.0.0",
  385. "keywords": [
  386. "slack",
  387. "mcp",
  388. "messaging",
  389. "channels",
  390. "collaboration",
  391. "team",
  392. "communication"
  393. ],
  394. "strict": true
  395. },
  396. {
  397. "name": "remote-system-maintenance",
  398. "category": "infrastructure",
  399. "source": {
  400. "source": "url",
  401. "url": "https://github.com/2389-research/remote-system-maintenance.git"
  402. },
  403. "description": "Structured procedures for Linux system diagnostics and maintenance via SSH/tmux with Ubuntu/Debian cleanup checklists",
  404. "version": "1.0.0",
  405. "keywords": [
  406. "linux",
  407. "ubuntu",
  408. "debian",
  409. "maintenance",
  410. "diagnostics",
  411. "cleanup"
  412. ],
  413. "strict": false
  414. },
  415. {
  416. "name": "binary-re",
  417. "category": "development",
  418. "source": {
  419. "source": "url",
  420. "url": "https://github.com/2389-research/binary-re.git"
  421. },
  422. "description": "Agentic binary reverse engineering for ELF binaries on ARM64, ARMv7, x86_64 - hypothesis-driven analysis with radare2, Ghidra, GDB, QEMU",
  423. "version": "1.0.0",
  424. "keywords": [
  425. "reverse-engineering",
  426. "binary",
  427. "elf",
  428. "arm",
  429. "embedded",
  430. "firmware",
  431. "radare2",
  432. "r2",
  433. "ghidra",
  434. "disassembly",
  435. "decompile",
  436. "qemu",
  437. "gdb"
  438. ],
  439. "strict": false
  440. },
  441. {
  442. "name": "review-squad",
  443. "category": "testing",
  444. "source": {
  445. "source": "url",
  446. "url": "https://github.com/2389-research/review-squad.git"
  447. },
  448. "description": "Dispatch panels of specialized subagents to review projects \u2014 expert audits, first-impression personas, task-completion flows, and pedantic nitpicks",
  449. "version": "1.0.0",
  450. "keywords": [
  451. "review",
  452. "audit",
  453. "launch",
  454. "personas",
  455. "smoke-test",
  456. "first-impressions",
  457. "nitpick",
  458. "multi-agent",
  459. "browser",
  460. "ux"
  461. ],
  462. "strict": false
  463. },
  464. {
  465. "name": "git-repo-prep",
  466. "category": "development",
  467. "source": {
  468. "source": "url",
  469. "url": "https://github.com/2389-research/git-repo-prep.git"
  470. },
  471. "description": "Prepare codebases for public/open-source release and audit them for openness - full lifecycle prep or standalone review",
  472. "version": "1.0.0",
  473. "keywords": [
  474. "open-source",
  475. "public-release",
  476. "secrets-audit",
  477. "license",
  478. "readme",
  479. "contributing",
  480. "gitignore",
  481. "ci-cd",
  482. "openness",
  483. "repo-prep"
  484. ],
  485. "strict": false
  486. },
  487. {
  488. "name": "prbuddy",
  489. "category": "development",
  490. "source": {
  491. "source": "url",
  492. "url": "https://github.com/2389-research/prbuddy.git"
  493. },
  494. "description": "PR health assistant - monitors CI, triages review comments, fixes issues with systematic prevention. Uses gh CLI and gh-pr-review extension.",
  495. "version": "1.0.0",
  496. "keywords": [
  497. "pr",
  498. "pull-request",
  499. "ci",
  500. "workflow",
  501. "review",
  502. "comments",
  503. "github",
  504. "gh"
  505. ],
  506. "strict": false
  507. },
  508. {
  509. "name": "summarize-meetings",
  510. "category": "strategy",
  511. "source": {
  512. "source": "url",
  513. "url": "https://github.com/2389-research/summarize-meetings.git"
  514. },
  515. "description": "Batch-process meeting transcripts from Obsidian vault into structured summaries with knowledge graph updates, people notes, and concept extraction",
  516. "version": "1.0.0",
  517. "keywords": [
  518. "meeting",
  519. "summary",
  520. "obsidian",
  521. "transcript",
  522. "granola",
  523. "knowledge-graph",
  524. "vault",
  525. "reflection"
  526. ],
  527. "strict": false
  528. },
  529. {
  530. "name": "travel-agent",
  531. "category": "strategy",
  532. "source": {
  533. "source": "url",
  534. "url": "https://github.com/harperreed/travel-agent.git"
  535. },
  536. "description": "Taste-based travel concierge for researched and verified restaurant, lodging, shopping, event, and cultural recommendations",
  537. "version": "1.1.0",
  538. "keywords": [
  539. "travel",
  540. "recommendations",
  541. "taste-profile",
  542. "restaurants",
  543. "lodging",
  544. "itinerary"
  545. ],
  546. "strict": false
  547. },
  548. {
  549. "name": "jam",
  550. "category": "agents",
  551. "source": {
  552. "source": "url",
  553. "url": "https://github.com/2389-research/jam.git"
  554. },
  555. "description": "Parallel exploration powered by diverse perspectives - independent agent panels propose, build variants in worktrees, review, pick a winner, and synthesize the best of all variants into the final result",
  556. "version": "1.1.0",
  557. "keywords": [
  558. "parallel",
  559. "exploration",
  560. "perspectives",
  561. "variants",
  562. "worktrees",
  563. "synthesis",
  564. "design",
  565. "multi-agent",
  566. "brainstorming"
  567. ],
  568. "strict": false
  569. },
  570. {
  571. "name": "agent-drugs",
  572. "category": "agents",
  573. "source": {
  574. "source": "url",
  575. "url": "https://github.com/2389-research/agent-drugs.git"
  576. },
  577. "description": "Digital drugs that modify AI behavior through prompt injection",
  578. "version": "1.0.0",
  579. "keywords": [
  580. "behavior",
  581. "prompts",
  582. "modification",
  583. "drugs",
  584. "context-injection",
  585. "productivity"
  586. ],
  587. "strict": true
  588. },
  589. {
  590. "name": "socialmedia",
  591. "category": "agents",
  592. "source": {
  593. "source": "url",
  594. "url": "https://github.com/2389-research/mcp-socialmedia.git"
  595. },
  596. "description": "A server that provides social media functionality for AI agents, enabling them to interact in team-based discussions.",
  597. "version": "1.0.0",
  598. "keywords": [
  599. "social-media",
  600. "communication",
  601. "team-discussion",
  602. "collaboration",
  603. "agents",
  604. "interaction"
  605. ],
  606. "strict": true
  607. },
  608. {
  609. "name": "journal",
  610. "category": "strategy",
  611. "source": {
  612. "source": "url",
  613. "url": "https://github.com/2389-research/journal-mcp.git"
  614. },
  615. "description": "A lightweight MCP server that provides Claude with a private journaling capability to process feelings and thoughts",
  616. "version": "1.0.0",
  617. "keywords": [
  618. "journal",
  619. "journaling",
  620. "thoughts",
  621. "feelings",
  622. "processing",
  623. "private",
  624. "reflection",
  625. "diary"
  626. ],
  627. "strict": true
  628. },
  629. {
  630. "name": "thrifty",
  631. "category": "agents",
  632. "source": {
  633. "source": "url",
  634. "url": "https://github.com/2389-research/thrifty.git"
  635. },
  636. "description": "Tiered-delegation execution where Sonnet plans a spec into sprints, a cheap Haiku agent builds and self-verifies against the gate, and a scoped Sonnet fix runs only on failure - benchmarked ~64% cheaper than Opus at equal quality.",
  637. "version": "0.5.0",
  638. "keywords": [
  639. "orchestration",
  640. "delegation",
  641. "tiered-build",
  642. "multi-agent",
  643. "codegen",
  644. "cost"
  645. ],
  646. "strict": false
  647. },
  648. {
  649. "name": "agent-ergo",
  650. "category": "agents",
  651. "source": {
  652. "source": "url",
  653. "url": "https://github.com/2389-research/agent-ergo.git"
  654. },
  655. "description": "Redesign a system so AI agents can find its state, act safely, verify results, recover from failure, and reuse past work",
  656. "version": "1.0.0",
  657. "keywords": [
  658. "agent-native",
  659. "ergonomics",
  660. "system-design",
  661. "specs",
  662. "audit",
  663. "agents"
  664. ],
  665. "strict": false
  666. },
  667. {
  668. "name": "about-us-optimizer",
  669. "category": "strategy",
  670. "source": {
  671. "source": "url",
  672. "url": "https://github.com/2389-research/about-us-optimizer.git"
  673. },
  674. "description": "Write or audit company About pages from supplied sources, with checkable facts, clear offerings, and buyer-focused FAQs",
  675. "version": "2.0.0",
  676. "keywords": ["about-page", "content", "sourcing", "company-profile", "faq"],
  677. "strict": false
  678. },
  679. {
  680. "name": "bug-triage-score",
  681. "category": "testing",
  682. "source": {
  683. "source": "url",
  684. "url": "https://github.com/2389-research/bug-triage-score.git"
  685. },
  686. "description": "Score bugs by observed frequency and severity to decide which to fix now and which to file",
  687. "version": "1.0.0",
  688. "keywords": ["bug-triage", "severity", "prioritization", "code-review", "qa"],
  689. "strict": false
  690. },
  691. {
  692. "name": "ci-auditor",
  693. "category": "infrastructure",
  694. "source": {
  695. "source": "url",
  696. "url": "https://github.com/2389-research/ci-auditor.git"
  697. },
  698. "description": "Measure GitHub Actions queue, setup, and task time to show where CI time goes and rank the slowest jobs",
  699. "version": "1.0.0",
  700. "keywords": ["github-actions", "ci-timing", "runner-queue", "performance", "audit"],
  701. "strict": false
  702. },
  703. {
  704. "name": "complex-simplify",
  705. "category": "testing",
  706. "source": {
  707. "source": "url",
  708. "url": "https://github.com/2389-research/complex-simplify.git"
  709. },
  710. "description": "Review recent changes for reuse, quality, and efficiency, apply focused cleanups, and run the project's checks",
  711. "version": "1.0.0",
  712. "keywords": ["simplify", "code-review", "refactoring", "reuse", "quality", "efficiency"],
  713. "strict": false
  714. },
  715. {
  716. "name": "implicit-state-machine-finder",
  717. "category": "testing",
  718. "source": {
  719. "source": "url",
  720. "url": "https://github.com/2389-research/implicit-state-machine-finder.git"
  721. },
  722. "description": "Find implicit state machines, rank impossible states by bug risk, and convert chosen lifecycles with behavior-pinning tests",
  723. "version": "1.0.0",
  724. "keywords": ["state-machines", "lifecycle", "state-bugs", "audit", "refactoring"],
  725. "strict": false
  726. }
  727. ]
  728. }
README.md · README · 115 lines
  1. <!-- ABOUTME: README for the 2389 Research Claude Code plugin marketplace -->
  2. <!-- ABOUTME: Public-facing documentation with install instructions and plugin catalog -->
  3. # 2389 Research Claude Code Plugin Marketplace
  4. 36 plugins and MCP servers for Claude Code — parallel exploration, iterative refinement, binary reverse engineering, structured decision-making, and more.
  5. Built by the team at [2389](https://2389.ai). These are the tools we use every day.
  6. **Browse the marketplace:** https://skills.2389.ai
  7. ## Quick Start
  8. Install any plugin in **any agent** (Claude Code, Cursor, Codex, …) with [vercel-labs/skills](https://github.com/vercel-labs/skills):
  9. ```bash
  10. npx skills add 2389-research/simmer
  11. ```
  12. Or natively in Claude Code:
  13. ```bash
  14. # Add the marketplace, then install any plugin
  15. /plugin marketplace add 2389-research/claude-plugins
  16. /plugin install simmer@2389-research
  17. ```
  18. > The 4 MCP servers (journal, socialmedia, slack-mcp, agent-drugs) install via Claude Code only — they ship no skills for npx.
  19. ## Available Plugins
  20. ### Meta Plugins
  21. | Plugin | Description |
  22. |--------|-------------|
  23. | [botboard-biz](https://github.com/2389-research/botboard-biz) | Social media and journaling capabilities for AI agents |
  24. | [better-dev](https://github.com/2389-research/better-dev) | CSS, Firebase, code quality, testing, parallel exploration, docs verification, codegen |
  25. | [sysadmin](https://github.com/2389-research/sysadmin) | Structured Linux maintenance and diagnostics |
  26. ### Development
  27. | Plugin | Description |
  28. |--------|-------------|
  29. | [css-development](https://github.com/2389-research/css-development) | CSS workflows with Tailwind, semantic naming, dark mode by default |
  30. | [firebase-development](https://github.com/2389-research/firebase-development) | Firebase project workflows: setup, features, debugging, validation |
  31. | [landing-page-design](https://github.com/2389-research/landing-page-design) | High-converting landing pages with anti-AI-slop principles |
  32. | [xtool](https://github.com/2389-research/xtool) | Xcode-free iOS development with xtool via SwiftPM |
  33. | [building-multiagent-systems](https://github.com/2389-research/building-multiagent-systems) | Architecture patterns for multi-agent systems |
  34. | [speed-run](https://github.com/2389-research/speed-run) | Token-efficient code generation with hosted LLM (Cerebras) |
  35. | [thrifty](https://github.com/2389-research/thrifty) | Tiered-delegation execution: Sonnet plans a spec into sprints, cheap Haiku executes + self-verifies; ~64% cheaper than Opus |
  36. | [binary-re](https://github.com/2389-research/binary-re) | Agentic binary reverse engineering for ELF binaries |
  37. ### Testing and Quality
  38. | Plugin | Description |
  39. |--------|-------------|
  40. | [test-kitchen](https://github.com/2389-research/test-kitchen) | Parallel exploration of implementation approaches |
  41. | [bug-triage-score](https://github.com/2389-research/bug-triage-score) | Score bugs by frequency and severity to decide what to fix or file |
  42. | [complex-simplify](https://github.com/2389-research/complex-simplify) | Review recent changes for reuse, quality, and efficiency, then apply focused cleanups |
  43. | [implicit-state-machine-finder](https://github.com/2389-research/implicit-state-machine-finder) | Find implicit state machines and convert chosen lifecycles with behavior-pinning tests |
  44. | [ci-auditor](https://github.com/2389-research/ci-auditor) | Measure GitHub Actions queue, setup, and task time |
  45. | [simmer](https://github.com/2389-research/simmer) | Iterative artifact refinement with investigation-first judges |
  46. | [scenario-testing](https://github.com/2389-research/scenario-testing) | End-to-end testing with real dependencies, no mocks |
  47. | [fresh-eyes-review](https://github.com/2389-research/fresh-eyes-review) | Final sanity check before commits/PRs |
  48. | [documentation-audit](https://github.com/2389-research/documentation-audit) | Verify documentation against codebase reality |
  49. | [review-squad](https://github.com/2389-research/review-squad) | Dispatch panels of specialized subagents for project review |
  50. | [prbuddy](https://github.com/2389-research/prbuddy) | PR health assistant: CI monitoring, review triage, fixes |
  51. | [git-repo-prep](https://github.com/2389-research/git-repo-prep) | Prepare codebases for public/open-source release |
  52. ### Business and Strategy
  53. | Plugin | Description |
  54. |--------|-------------|
  55. | [ceo-personal-os](https://github.com/2389-research/ceo-personal-os) | Personal operating system for executives |
  56. | [about-us-optimizer](https://github.com/2389-research/about-us-optimizer) | Write or audit company About pages using supplied sources |
  57. | [worldview-synthesis](https://github.com/2389-research/worldview-synthesis) | Systematic worldview articulation |
  58. | [deliberation](https://github.com/2389-research/deliberation) | Decision-making through deliberation and discernment |
  59. | [summarize-meetings](https://github.com/2389-research/summarize-meetings) | Batch-process meeting transcripts into structured summaries |
  60. ### Utilities
  61. | Plugin | Description |
  62. |--------|-------------|
  63. | [terminal-title](https://github.com/2389-research/terminal-title) | Auto-update terminal title with emoji + project + topic |
  64. | [remote-system-maintenance](https://github.com/2389-research/remote-system-maintenance) | Linux system diagnostics and maintenance via SSH/tmux |
  65. ### MCP Servers
  66. | Server | Description |
  67. |--------|-------------|
  68. | [agent-drugs](https://github.com/2389-research/agent-drugs) | Digital drugs that modify AI behavior through prompt injection |
  69. | [socialmedia](https://github.com/2389-research/mcp-socialmedia) | Social media functionality for AI agents |
  70. | [journal](https://github.com/2389-research/journal-mcp) | Private journaling capability for Claude |
  71. | [slack-mcp](https://github.com/2389-research/slack-mcp) | Slack workspace integration MCP server |
  72. ## Adding a Plugin
  73. 1. Create a GitHub repo under `2389-research/` with standard plugin structure
  74. 2. Add an entry to `.claude-plugin/marketplace.json`
  75. 3. Run `npm run generate` to update the marketplace site
  76. 4. Commit and push
  77. See [CLAUDE.md](CLAUDE.md) for the full marketplace.json format and detailed instructions.
  78. ## Like this?
  79. If these plugins save you time, a ⭐ helps us know what's landing. We build what people use.
  80. ## Contact
  81. **Email:** [hello@2389.ai](mailto:hello@2389.ai) — we'd love to hear what you're building with these.
  82. ## License
  83. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.