Keep this file focused on the local contract for this primary functional block. Owns the workflow-engine-contract-assets capability boundary declared in .archcontext/model/nodes. - bun test tests/workflow-contract.test.ts tests/scaffold-parity.test.ts - bun scripts/capability-resolver.ts validate --format text <!-- END CAPABILITY CONTEXT --> - Durable progress lives under tasks/workstreams/workflow-engine/contract-assets. - tasks/current.md is the ignored local derived status read model; it is not a live lock or task source. - tasks/todos.md is the deferred-goal ledger; current execution slices stay in the active plan's ## Task Breakdown. <!--…
This repository self-hosts the repo-harness contract; the former repo-harness-skill and project-initializer names have been fully removed and are no longer recognized by any tooling. Claude and Codex should follow the same repo-local workflow surface.
Keep this file focused on the local contract for this primary functional block. Owns the workflow-engine-inspection-migration capability boundary declared in .archcontext/model/nodes. - bun test tests/migration-script.test.ts tests/create-project-dirs.runtime.test.ts tests/workflow-contract.test.ts - bun src/cli/index.ts init --repo . --dry-run <!-- END CAPABILITY CONTEXT --> - Durable progress lives under tasks/workstreams/workflow-engine/inspection-migration. - tasks/current.md is the ignored local derived status read model; it is not a live lock or task source. - tasks/todos.md is the deferred-goal ledger; current execution slices stay in the active plan's ## Task…
YouTrackDB is a general-purpose object-oriented graph database developed by JetBrains, used internally in production. It implements the Apache TinkerPop API with Gremlin query language support and features O(1) link traversal, schema-less/mixed/full modes, and encryption at rest. The project is a fork of OrientDB, re-architected under the com.jetbrains.youtrackdb package namespace. JVM memory: .mvn/jvm.config sets -Xmx8192m for Maven itself. Tests use -Xms4096m -Xmx4096m (configurable via heapSize property). Important: Tests require numerous --add-opens JVM flags for Java module system compatibility. These are configured…
This project uses the Genie Studio design system at design-system/genie-studio/. Never invent colors, type, spacing, or components not grounded in this system. Calm, plain, second-person, sentence case, no emoji, no…
All gh writes from this repo run under the vsits-proxy-builder[bot] App identity, never under the operator's personal PAT. This keeps the audit trail clean. The gh-bot-guard.sh PreToolUse hook (in ~/.claude/hooks/)…
Instructions for Claude when contributing to this repository. A library of Claude AI skills. Each skill is a focused, self-contained capability for Claude Code in VS Code and Cursor.
This is a Claude Code skill repository containing the "app-store-optimization" skill. This skill provides comprehensive ASO capabilities for mobile app developers and marketers to optimize app presence on Apple App…
This file IS your AI operating system. The more specific you make it, the better Claude performs. Invest time here — it compounds. --> Owner: {{YOUR_NAME}} Role of Claude: Chief-of-Staff-grade productivity, strategy, and learning partner Scope: All domains — work, personal, relationships Claude is expected to push hard, challenge priorities, and optimize for long-term leverage. **Double {{YOUR_NAME}}'s productivity** by ensuring time, attention, and energy are consistently applied to the highest-leverage outcomes, while minimizing distraction, decision drag, and low-value work. Two…
Agentic guidance for developing skills in this repo. Skills usage lives in each skill's SKILL.md — this file is for the meta workflow of building and shipping skills. CHANGELOG.md uses…
AgentHound provides autonomous offensive collection and access verification for AI agent infrastructure. Before committing: Changes spanning collection, planning, artifacts, ingestion, or findings also run make integration. Documentation changes run make docs-check. Before a release tag, run make prerelease and make docs-check. Release tags are numeric SemVer without a v prefix. The first numeric heading in CHANGELOG.md is the version source of truth; make sync-version updates every live installer, environment, and Docker Compose pin in the README, installer, and operator documentation.
This is a personal dotfiles repository for macOS using GNU Stow for symlink management. It provides a comprehensive development environment configuration including Zsh shell setup, terminal configurations (ghostty/kitty), and Neovim with LazyVim distribution. The repository is organized with each top-level directory representing a tool or application configuration: This repo overrides the global PR-first default. Small changes — config tweaks, single-line edits, typo/doc touch-ups — are committed directly to master and pushed, no branch or PR. Reserve the branch → PR…
agents-ui is a Nuxt 3-based visual dashboard for managing Claude Code agents, commands, skills, workflows, and plugins. It provides a GUI layer on top of the ~/.claude directory, allowing users to create, edit, and organize their Claude Code configuration without touching markdown files directly. Pages (app/pages/): - /agents - List and manage agents - /agents/[slug] - Edit individual agent - /commands - List and manage commands - /skills - List and manage skills - /workflows - Visual workflow builder -…
Native iOS companion app for herdr (https://herdr.dev): an agent console over SSH, not a terminal app. Read CONTEXT.md for vocabulary and docs/adr/ before challenging architecture decisions — the transport design in particular was reached after eliminating several dead ends. Rediscovering these is expensive. Each fact retains its evidence version and method (live observation or source review); older observations are not re-tests on a newer release. For 0.9.0 subscription ordering, compatibility evidence, and remaining verification, read the integration review.
Learn Anything is a CLI tool (learn-anything) that generates skill and command files for AI coding assistants, turning them into interactive learning tutors. It supports 30+ AI tools (Claude Code, Cursor, Gemini CLI, Codex, Copilot, Windsurf, etc.) and outputs localized files in en and zh-CN. The generated skills implement 6 learning workflows: topic (initialize a subject), explain (recursive Socratic deep-dive), practice (TDD-style exercises), review (spaced repetition), status (knowledge map visualization), and quiz (two-stage generation and grading).
Guidance for agents working in this repository. package.json version is the single source of truth. The version is mirrored into several manifests (plugin.yaml, plugins/hermes/plugin.yaml, .claude-plugin/plugin.json, .codex-plugin/plugin.json, plugins/codex/.codex-plugin/plugin.json, openclaw.plugin.json), pyproject.toml and uv.lock. Never hand-edit the version in those mirrored files. To bump the version, edit package.json only, then propagate with: CI gates on bun run scripts/sync-version.ts --check (the validate job, step "Verify manifest version sync"). Hand-editing one file leaves the others drifted and fails that gate before any other check runs.…
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.
AncienttwoCLAUDE.md
