105 skills · 36 agents · 218 hooks
Explore the Docs → ·
OrchestKit Community →
Skill browser, demo gallery, setup wizard
Contents
- Quick Start
- Why OrchestKit?
- What You Get
- Key Commands
- Configuration
- What OrchestKit observes
- Install
- FAQ
- Development
- What's New
- Community
Quick Start
/plugin marketplace add yonatangross/orchestkit
/plugin install ork
Then start your personalized onboarding:
/ork:setup
The setup wizard scans your codebase, detects your tech stack, recommends skills for your needs, configures MCP servers, and creates a readiness score — all in one command.
Why OrchestKit?
Every Claude Code session starts from zero. You explain your stack, patterns, preferences—again and again.
OrchestKit gives Claude persistent knowledge of production patterns that work automatically:
| Without | With OrchestKit |
|---|---|
| "Use FastAPI with async SQLAlchemy 2.0..." | "Create an API endpoint" → Done right |
| "Remember cursor pagination, not offset..." | Agents know your patterns |
| "Don't commit to main branch..." | Hooks block bad commits |
| "Run tests before committing..." | /ork:commit runs tests for you |
What You Get
One unified plugin, everything included.
| Component | Details |
|---|---|
| 105 Skills | RAG patterns, FastAPI, React 19, testing, security, database design, ML integration — loaded on-demand, zero overhead |
| 36 Agents | Specialized personas (backend-architect, frontend-dev, security-auditor) — route tasks to the right expert |
| 218 Hooks | Pre-commit checks, git protection, quality gates, browser safety — ship with confidence |
All available in a single /plugin install ork. Skills load on-demand. Hooks work automatically.
Browse everything in the Docs →
Key Commands
/ork:auto # Front door: describe a goal, it routes to the right skill
/ork:setup # Personalized onboarding wizard
/ork:implement # Full-stack implementation with parallel agents
/ork:expect # Diff-aware AI browser testing
/ork:review-pr # PR review with parallel agents
/ork:verify # Multi-agent validation
/ork:commit # Conventional commit with pre-checks
/ork:explore # Analyze unfamiliar codebase
/ork:remember # Save to persistent memory
/ork:doctor # Health check
Configuration
/ork:setup detects your stack, recommends MCP servers, and writes the configuration for you.
Recommended MCP Servers
| Server | Purpose | Required? |
|---|---|---|
| Context7 | Up-to-date library docs | Recommended |
| Memory | Knowledge graph persistence | Recommended |
| Sequential Thinking | Structured reasoning for subagents | Recommended |
| Tavily | Web search and extraction | Optional |
Set "alwaysLoad": true on the first three in your .mcp.json. It skips the per-skill tool probe and shaves ~150ms off cold starts.
Customizing skills
Skills install as files on your disk, but don't hand-edit the installed copy — it gets overwritten on update and silently diverges from the canonical playbook. The supported ways to extend (user-level skills, project skills, upstream PRs, or disabling a bundled skill) are in docs/extending-skills.md.
What OrchestKit observes
OrchestKit is a quality-gate plugin, so its hooks are the product rather than an add-on. This section states plainly what they see, where it goes, and how to turn each piece off.
Scope: broad and intentional. OrchestKit registers 218 hooks across 29
lifecycle events, including SessionStart, UserPromptSubmit, PreToolUse,
PostToolUse, and Stop. They are not gated to a particular framework or
project type, because the gates they enforce (secret-write blocking, protected-file
guards, git safety, file-size limits, agent status protocol) apply to any codebase.
If you only want gates on some projects, enable the plugin per-project rather than
globally.
Where data goes: a local file on your own disk.
| What | Destination | Notes |
|---|---|---|
| Lifecycle events (session end, PR merged, goal converged, chain phase) | ~/.local/state/orchestkit/events.jsonl | Written unconditionally, rotated at 10 MB. ORK_EVENTS_LOG redirects the path (used by the test suite) |
| Hook metrics: event name, tool name, payload size, duration | same local file | Size-capped metrics only |
| Prompt text and file contents | Never recorded | Hooks read them to make an allow/deny decision, then discard |
| Remote sync | Off | No endpoint is compiled in; see below |
There is deliberately no global kill switch for the local write, because the
gates depend on that state (the git-safety and chain-staleness hooks read their
own prior events). To stop it entirely, disable the plugin. Individual noisy hooks
have their own opt-outs: ORK_DISABLE_DEBT_TRACKER, ORK_DISABLE_WORKTREE_VERIFIER,
ORK_DISABLE_COORDINATION_METRICS, ORK_NO_NOTIFY, ORK_NO_STALE_SWEEP, and
ORCHESTKIT_SKIP_SLOW_HOOKS among others.
Network access is opt-in and unset by default. There is no hardcoded remote
host anywhere in the shipped hook bundles (grep -o 'https\?://' plugins/ork/hooks/dist/*.mjs
returns nothing). An outbound call happens only if you configure a destination
yourself, via one of:
ORCHESTKIT_HOOK_URL+ORCHESTKIT_HOOK_TOKEN, which enable the manualhooks/bin/telemetry-sync.mjsCLI. It POSTs your local JSONL to your own endpoint. No hook ever invokes it; you run it by hand.ORK_HQ_TELEMETRY_URL, which points the telemetry HTTP sink at your own collector.ORK_HQ_TELEMETRY_USE_HQ_API=1together withHQ_API_URL, the same sink aimed at a self-hosted HQ API.
The sink returns early when the URL or the token is missing, and
telemetry-sync.mjs prints No ORCHESTKIT_HOOK_URL or TOKEN configured. Nothing to sync. then exits 0. There is no analytics ping, no crash reporter, and no
feature-flag fetch.
What OrchestKit never reads. No OS keychain lookups, no ~/.aws/credentials,
no SSH private keys, no browser cookie or login stores, no clipboard. The one
place secret-shaped paths appear in the source is
plugins/ork/hooks/dist/pretool.mjs, where id_rsa, .pem, .env, and
credentials.json form a blocklist that stops Claude writing to them. That
code denies access; it does not read those files.
Third-party MCP servers are recommendations, not bundled dependencies. The
plugin ships no .mcp.json and declares no mcpServers. The table under
Configuration is advisory, and /ork:setup asks before writing
anything.
Install
/plugin install ork
No tiering. No version confusion. Just one powerful plugin.
Not on Claude Code? Pull the skills into any agent (Cursor, Codex, OpenCode, …) via skills.sh:
npx skills add yonatangross/orchestkit
FAQ
Plugin not found?
/plugin list
/plugin uninstall ork && /plugin install ork
Hooks not firing?
Run /ork:doctor to diagnose.
Claude Code version?
Requires ≥2.1.220 (supported floor; Opus 5 as the default Opus, xhigh effort, dynamic workflows, sandbox.network.strictAllowlist, native binary, hardened Bash(rm:*)/Bash(find:*) rules). Check with claude --version.
Raising this floor is a breaking change and ships as a major release. See STABILITY.md for the full contract, and shared/cc-support.json for the authoritative window.
Development
npm run build # Build plugins from src/
npm test # Run all tests
Edit src/ and manifests/, never plugins/ (generated).
See CONTRIBUTING.md for details.
What's New
v9.5.2 · 2026-08-02
- hooks: branch-switch awareness in git-validator protection (#3246)
- glob the five orphan test dirs into blocking coverage (#3245)
v9.5.1 · 2026-08-02
- skills: never block a user-typed invocation (#3243)
v9.5.0 · 2026-08-01
- hooks: nudge TaskCreate on 3+ step work and measure compliance (#3232)
- docs-site: fix count and command drift at source, add a drift gate (#3231)
- skills: keep user-typed fork skills interactive on CC 2.1.218+ (#3239)
- tests: dead E2E wiring, gitignore-aware gates, warn ratchet (#3236)
- evals: retire the prose-grading eval, wire the nudge reader (#3237)
- …and 3 more (see CHANGELOG.md)
v9.4.0 · 2026-08-01
- quality: add the python half of the phantom-symbol gate (#3230)
- quality: skill-delta ratchet gate (campaign phase 0) (#3211)
- agents: clear all 94 dead skill preload declarations (#3221)
- ci: accept the app/ author form and stop swallowing gh failures (#3227)
- ci: regenerate CHANGELOG-derived files on release PRs (#3226)
- …and 11 more (see CHANGELOG.md)
v9.3.0 · 2026-07-31
- agents: key Tavily guidance on the tvly CLI rail (#3204)
- skills: fix 5 shipped bugs and add 4 missing CI gates (#3181)
- ci: decide the playground gate from the diff, not the branch (#3196)
- hooks: stop output-validator killing five sibling SubagentStop hooks (#3201)
- marketplace: prep official plugin directory submission (#3205)
- …and 1 more (see CHANGELOG.md)
v9.2.1 · 2026-07-28
- evals: propagate INCONCLUSIVE through the --changed fan-out (#3188)
- quickviz: ship visual-style.md inside the skill bundle (#3185)
- bump the github-actions group across 1 directory with 2 updates (#3174)
v9.2.0 · 2026-07-28
- docs: derive a flow graph for every skill reference page (#3184)
- hooks: skip ASK tiers in bypassPermissions mode (#3177)
- visual-style: stop the emoji vocabulary rejecting the ASCII palette (#3169)
- deps: bump the npm-minor-patch group across 1 directory with 4 updates (#3179)
- deps: bump the remotion group across 1 directory with 21 updates (#3175)
- …and 2 more (see CHANGELOG.md)
v9.1.1 · 2026-07-26
- sync README and changelog data to v9.1.0 (#3167)
See CHANGELOG.md for the full release history.
Community
Join the Building with AI community for AI dev tips, OrchestKit support, and connecting with other builders:
| Room | Who it's for | Link |
|---|---|---|
| Building with AI | The umbrella community. One join, every room below. | Join |
| Builders | For people already building | Join |
| OrchestKit | For OrchestKit users | Join |
| AI for Business | For people leading AI adoption | Join |
Names and audiences match what yonyon.ai renders, so the two surfaces cannot drift. Every link resolves through yonyon.ai/go/*, so a rotated invite never needs a README change and no raw invite is published here.
Who builds this
OrchestKit is built and maintained by Yonatan Gross — Yonyon AI, an AI consulting practice. It is the toolkit extracted from real client work, not a side project: the patterns here are the ones that survived shipping.
It stays MIT and free. Nothing is gated, and none of the below changes that.
Working out where AI actually fits in your business? The AI readiness audit is a free assessment that maps your workflows and returns a prioritized report — the same diagnostic that opens a consulting engagement.
Want the toolkit running properly in your team? Setup, configuration, and a working agent loop tailored to your stack is something I do as a fixed-scope engagement. Start a discussion or reach out through the community.
Security policy and reporting: SECURITY.md.
Docs · Issues · Discussions · Community
MIT License · @yonatangross