yonatangross/orchestkit

The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stable (v9.x), or `ork-alpha` for the v10 line, which ships daily.

This repository also configures its own agents. See what orchestkit tells them →

264Stars on the repository
236Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

yonatangross/orchestkit

Cursor rule Cursor

Adversarial Refutation Engine. Shared blind-refuter protocol that removes self-preferential bias from evaluative skills — the producer of a finding can't be its own fair judge.

not rated 236 +7 yesterday A 35 tokens original MIT

anti-sycophancy

02

yonatangross/orchestkit

Cursor rule Cursor

Anti-Sycophancy Response Protocol. Prevents performative agreement that buries critical findings.

not rated 236 +7 yesterday A 18 tokens original MIT

cc-bare-auth-gotcha

03

yonatangross/orchestkit

Cursor rule Cursor

Status: confirmed CC 2.1.81–2.1.143 · upstream bug filed anthropics/claude-code#60155 · prior incident orchestkit#1629.

not rated 236 +7 yesterday C 28 tokens original MIT

yonatangross/orchestkit

Cursor rule Cursor

Chart Encoding Standard. Governs the DATA-MARK layer of every chart OrchestKit emits (playground, dashboard, infographic, MCP visual, multi-surface). ork does not own chart color science — it rents it from CC's /dataviz. The difference between an accessible, validated chart and an eyeballed rainb...

not rated 236 +7 yesterday A 67 tokens original MIT

code-quality

05

yonatangross/orchestkit

Cursor rule Cursor

Code Quality Thresholds. Keep functions under 50 lines.

not rated 236 +7 yesterday A 12 tokens original MIT

docstring-standards

06

yonatangross/orchestkit

Cursor rule Cursor

Docstring Standards. All public functions (no prefix) should have """docstring""" documentation.

not rated 236 +7 yesterday A 20 tokens original MIT

evidence-replay

07

yonatangross/orchestkit

Cursor rule Cursor

Evidence Replay Gate. Producer findings in evaluative pipelines are inadmissible until the orchestrator has deterministically replayed their cited evidence, so hallucinated citations never reach a verdict, score, or report.

not rated 236 +7 yesterday A 40 tokens original MIT

license-compliance

08

yonatangross/orchestkit

Cursor rule Cursor

License Compliance. When installing new dependencies, check their license before adding to production projects.

not rated 236 +7 yesterday A 17 tokens original MIT

yonatangross/orchestkit

Cursor rule Cursor

Playground Visual Standard. Governs the visual quality of every playground OrchestKit emits. The difference between a considered product demo and a generic AI dashboard is the specific values in this file.

not rated 236 +7 yesterday A 38 tokens original MIT

sections

10

yonatangross/orchestkit

Cursor rule Cursor

Shared Cross-Cutting Rules. Cross-cutting evidence requirements for all skill completion claims.

not rated 236 +7 yesterday A 17 tokens original MIT

yonatangross/orchestkit

Cursor rule Cursor

Shell Count Correctness. Counting lines or files in shell is the most common thing our audit and telemetry scripts do, and every recipe below has already shipped a wrong number in this repo. A count that is silently low reads as a passing gate.

not rated 236 +7 yesterday A 49 tokens original MIT

yonatangross/orchestkit

Cursor rule Cursor

Untrusted Input Quarantine. Prompt-injection defense for skills that read GitHub issue/PR/CI content — separate the agent that READS untrusted text from the agent that ACTS.

not rated 236 +7 yesterday A 38 tokens original MIT

verification-gate

13

yonatangross/orchestkit

Cursor rule Cursor

Verification Gate. Prevents premature completion claims across all skills.

not rated 236 +7 yesterday A 11 tokens original MIT

visual-style

14

yonatangross/orchestkit

Cursor rule Cursor

Visual Style — ASCII Art and Emoji Usage. OrchestKit leans into ASCII art and semantic emojis for visual scanability — but only with a fixed vocabulary, only where they earn their keep, and never where they break greppability, byte budgets, or accessibility.

not rated 236 +7 yesterday A 54 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: