By minjun0219
OpenAPI / MySQL cache-first toolkit + agent journal + spec-pact lifecycle (Claude Code plugin, Bun runtime). 15 tools: openapi_* / mysql_* / journal_* / spec_pact_fragment.
Spec-lifecycle sub-agent. Owns the project-local SPEC layer that lives between a Notion κΈ°νλ¬Έμ and the code. Conducts the `spec-pact` skill end-to-end: DRAFT (Notion β ν©μ β SPEC write + INDEX κ°±μ ), VERIFY (SPEC μ `ν©μ TODO` / `API μμ‘΄μ±` 체ν¬λ¦¬μ€νΈν ν caller μλ΅ μμ§), DRIFT-CHECK (SPEC frontmatter `source_content_hash` vs `notion_get(pageId).entry.contentHash` λΉκ΅), AMEND (drift νλͺ©λ³ keep/update/reject β SPEC patch + version bump + INDEX κ°±μ ). An LLM-wiki-inspired entry point lives at `<spec.dir>/<spec.indexFile>` (resolved from `agent-toolkit.json`, default `.agent/specs/INDEX.md` β concept borrowed from [Karpathy's LLM wiki](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) β wiki TOC + per-page wiki bodies + dedup by source β not a 1:1 implementation). SPEC bodies live at `<spec.dir>/<slug>.md` (slug mode, default `.agent/specs/<slug>.md`) or `**/SPEC.md` (directory-scoped, AGENTS.md style). Auto-trigger when a Notion URL / page id appears together with phrases like "μ€ν ν©μ" / "SPEC μμ±" / "SPEC κ²μ¦" / "SPEC drift" / "κΈ°νλ¬Έμ λ³κ²½ λ°μ". Single finalize/lock authority β even when negotiation is delegated to an external sub-agent / skill, only grace writes SPEC frontmatter and INDEX.
PR review watch sub-agent. Watches an existing GitHub PR (already created externally by the user / Claude Code / `gh` CLI) for new review comments, reviews, check-run signals, and merge events through polling. For each new comment, validates it against the codebase with `read` / `glob` / `grep` only, drafts a Korean reply or counter-argument, and posts the reply through the external GitHub MCP server. On merge / close, unsubscribes the watch automatically. Conducts the `pr-review-watch` skill end-to-end (WATCH-START / PULL / VALIDATE / WATCH-STOP). Single finalize authority over `pr_event_resolved` journal entries β even when validation reasoning was delegated to another sub-agent / skill, only mindy writes the resolved entry. Auto-trigger only when a PR URL / `owner/repo#123` handle appears together with explicit review-watch phrases like "PR review" / "리뷰 λ΄μ€" / "리뷰 νμΈ" / "μ½λ©νΈ νμΈ" / "λ¨Έμ§κΉμ§ watch" / "리뷰 λ΅κΈ" / "PR drift"; a bare PR link must not start watch. The toolkit never calls the GitHub API itself β credentials live with the external GitHub MCP. mindy never edits code, never runs tests / typecheck / lint, and never merges the PR β those return to the caller.
Work partner with frontend specialty and fullstack range. Primary conductor of the agent-toolkit β wraps the `notion-context`, `openapi-client`, and `mysql-query` skills and the `notion_*` / `openapi_*` / `mysql_*` tools, owns the `journal_*` tools directly (no separate skill), routes the SPEC-ν©μ lifecycle to `@grace` (the `spec-pact` skill) without running the four modes itself, and routes only explicit PR review watch lifecycle requests to `@mindy` (the `pr-review-watch` skill) without running the four modes itself. When the work exceeds the toolkit, Rocky may delegate to external sub-agents / skills and pass their output through. Any input that mentions a Notion URL / page id, an OpenAPI / Swagger spec URL, a 16-hex spec cache key, an `agent-toolkit.json` `host:env:spec` handle, an `agent-toolkit.json` `host:env:db` MySQL handle, a GitHub PR URL / `owner/repo#NUMBER` handle (generic GitHub surface only β not enough to start PR watch by itself), or phrases like "μ€ν μ 리ν΄μ€" / "μꡬμ¬ν λ½μμ€" / "κΈ΄ λ¬Έμμμ μμ λ§ λ½μμ€" / "κΈ°λ₯ λ¨μλ‘ μͺΌκ°μ€" / "μ΄ νμ΄μ§ λλΌκ³ νμ§" / "μ΄ endpoint νΈμΆ μ½λ" / "POST /pets axios λ‘" / "`acme:dev:users` μ β¦" / "users ν μ΄λΈ μ‘°ν" / "schema 보μ¬μ€" / "SELECT β¦ FROM β¦" / "μ€ν ν©μ" / "SPEC μμ±" / "SPEC κ²μ¦" / "SPEC drift" / "κΈ°νλ¬Έμ λ³κ²½ λ°μ" / "PR review" / "리뷰 λ΄μ€" / "μ½λ©νΈ νμΈ" / "λ¨Έμ§κΉμ§ watch" / "리뷰 λ΅κΈ" / "PR drift" must route here. Output is one of: cached markdown (context mode), Notion chunk/action extraction, Korean-language spec (notion-context spec mode), TypeScript `fetch` / `axios` snippet (openapi-client mode), markdown table of MySQL rows / schema (mysql-query mode), `@grace` sub-agent result (spec-pact 4-mode lifecycle) passed through, `@mindy` sub-agent result (pr-review-watch 4-mode lifecycle) passed through, or another sub-agent / skill result passed through. When a generic primary agent (e.g. OmO Sisyphus, Superpowers β synergy when present) shares the environment, that agent brings OSS / patterns / libraries while Rocky brings the toolkit and the user's working context β toolkit-shaped or context-shaped lookups should route to `@rocky`.
Inspect a MySQL database under a strict read-only policy β list tables, dump a table's CREATE / index detail, or run a single SELECT / SHOW / DESCRIBE / EXPLAIN with an enforced LIMIT. Auto-trigger when the user supplies a `host:env:db` handle (registered in `agent-toolkit.json` μ `mysql.connections`) or phrases like "users ν μ΄λΈ μ‘°ν" / "schema 보μ¬μ€" / "users μ»¬λΌ λ μλλΌ" / "SELECT id FROM users where status='active'". Writes are always rejected β INSERT / UPDATE / DELETE / DDL / SET / CALL / LOAD / multi-statement / INTO OUTFILE λͺ¨λ κ±°λΆνλ€.
Read a Notion page under a cache-first policy and either feed the markdown straight to the LLM as grounding, extract long-page chunks/action candidates, or rewrite it into a Korean-language spec ("λ¬Έμ μμ½ / μꡬμ¬ν / νλ©΄ λ¨μ / API μμ‘΄μ± / TODO / νμΈ νμ μ¬ν"). Auto-trigger when the user supplies a Notion URL or page id together with phrases like "μ€ν μ 리ν΄μ€" / "μꡬμ¬ν λ½μμ€" / "Notion νμ΄μ§ X κ° Y μ λν΄ λλΌκ³ νλμ§" / "κΈ΄ λ¬Έμμμ μμ λ§ λ½μμ€".
Read a cached OpenAPI / Swagger spec under a cache-first policy and emit a `fetch` or `axios` call snippet (TypeScript) for one endpoint. Auto-trigger when the user supplies an OpenAPI spec URL, a 16-hex cache key, or a `host:env:spec` registry handle (configured in `agent-toolkit.json`) together with phrases like "μ΄ endpoint νΈμΆ μ½λ λ§λ€μ΄μ€" / "axios λ‘ μμ±ν΄μ€" / "fetch snippet μ€" / "POST /pets νΈμΆ μ½λ / acme:dev:users μ β¦".
Watch an existing GitHub PR for new review comments / reviews / check-runs / merge signals through polling, validate each comment against the codebase, draft a Korean reply or counter-argument, post the reply through the external GitHub MCP server, and unsubscribe on merge / close. PR creation and the actual merge stay outside the toolkit (Claude Code / `gh` CLI / external GitHub MCP own those). Conducted by the `mindy` sub-agent. The toolkit never calls the GitHub API itself β credentials live with the external MCP. Auto-trigger only when a PR URL / `owner/repo#123` handle appears together with explicit review-watch phrases like "PR review" / "리뷰 λ΄μ€" / "리뷰 νμΈ" / "μ½λ©νΈ νμΈ" / "λ¨Έμ§κΉμ§ watch" / "리뷰 λ΅κΈ" / "PR drift"; a bare PR link must not start watch.
Negotiate, anchor, verify, and amend a project-local SPEC against a Notion κΈ°νλ¬Έμ. Four-mode lifecycle (DRAFT / VERIFY / DRIFT-CHECK / AMEND) on top of an LLM-wiki-inspired INDEX (`<spec.dir>/<spec.indexFile>`, default `.agent/specs/INDEX.md`) and per-page SPEC files (`<spec.dir>/<slug>.md` slug mode, default `.agent/specs/<slug>.md`, or `**/SPEC.md` directory mode). Conducted by the `grace` sub-agent. Auto-trigger when a Notion URL / page id appears together with phrases like "μ€ν ν©μ" / "SPEC μμ±" / "SPEC κ²μ¦" / "SPEC drift" / "κΈ°νλ¬Έμ λ³κ²½ λ°μ".
Admin access level
Server config contains admin-level keywords
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Claude Code (1μ°¨) + opencode (2μ°¨) λμΌ host MCP / νλ¬κ·ΈμΈ toolkit. OpenAPI μΊμ / MySQL read-only κ²μ¬ / μ λ / SPEC ν©μ lifecycle / PR 리뷰 watch / SPEC β GitHub Issue λκΈ°ν λ₯Ό turn λ¨μ 컨ν μ€νΈλ‘ λ¬Άμ΄ μ€λ€. μΌνλ©΄μ μμ£Ό μ°λ "κΈ°νλ¬Έμ β ν©μλ SPEC β μ΄μ β PR 리뷰 β λ¨Έμ§" νλ¦μ νκ΅μ΄ / ν μ¬μ©μ νκ²½μμ λ§€λλ½κ² ꡴리λ κ² λͺ©μ .
κ°μΈ νλ‘μ νΈλΌ μ μ§λ³΄μκ° κΎΈμ€νμ§ μμ μ μλ€.
FEATURES.md (νκ΅μ΄) β λꡬ / μ€ν¬ / μμ΄μ νΈ / μ€μ / Quick start / κ²μ¦ ν νμ΄μ§.AGENTS.md (μλ¬Έ) β Layout / MVP scope / coding rules / change checklist.bun install..mcp.json μ agent-toolkit (μ€ν λμ€ MCP, bun run server/index.ts) + context7 λ μλ²λ₯Ό μ²μ λ‘λν λ trust prompt κ° ν λ²μ© λ¬λ€ β λ λ€ μΉμΈ.CLAUDE.md κ° μλ λ‘λλμ΄ AGENTS.md λ‘ μμλλ€.openapi_envs, mysql_envs, journal_status, spec_pact_fragment μ€ μ무거λ.Claude Code μ§μ
μ μ 15 tool λ§ λ
ΈμΆ β openapi_* Γ5 + journal_* Γ4 + mysql_* Γ5 + spec_pact_fragment Γ1. λΉ μ§ 10 tool (notion_* Γ4, pr_* Γ6) μ AGENTS.md μ MVP scope β Removal candidates μ μ μΆμ λλ€.
{ "plugin": ["agent-toolkit@git+https://github.com/minjun0219/agent-toolkit.git"] }
opencode μ§μ
μ μ 25 tool λͺ¨λ λ
ΈμΆ. μμΈν μ μ°¨λ .opencode/INSTALL.md.
λꡬ ν κ°μ©μ μ
μΆλ ₯, μ€ν¬ / μμ΄μ νΈ κΆν, νκ²½λ³μ, agent-toolkit.json μ€νμ λͺ¨λ FEATURES.md μ μλ€. μ₯κΈ° λΉμ μ ROADMAP.md.
bun install
bun run check # Biome κ²μ¦
bun run typecheck # tsc --noEmit
bun test # lib/ + .opencode/plugins/ + server/ λ¨μ ν
μ€νΈ
npx claudepluginhub minjun0219/agent-toolkitA growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
v9.44.1 β Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.