Public, open-source home of @pascal-app/{core,viewer,editor,mcp} and the standalone editor app. Consumed both as npm packages and (in pascalorg/private-editor) as a git submodule. CLAUDE.md, GEMINI.md, and .github/copilot-instructions.md are symlinks to this file. Codex reads this file directly. Details, examples, and rationale live in wiki/architecture/layers.md, wiki/architecture/viewer-isolation.md, wiki/architecture/systems.md, wiki/architecture/renderers.md, wiki/architecture/tools.md. Read the relevant page in wiki/architecture/ before writing code. The page list lives in wiki/architecture/README.md. As a minimum: Invoke the review-architecture skill (.agents/skills/review-architecture/SKILL.md). It loads the required architecture pages, fetches the diff, classifies…
Every release goes through the release skill: .agents/skills/release/SKILL.md. Read it in full before running eas update, eas build, eas submit, any pnpm ota* or pnpm release:* script, or dispatching a release workflow. That covers preview and production OTA updates, native builds, store submissions, and CLI publishes. The rule the skill opens with is the one that is never skipped: release from a local main that is exactly origin/main, checked against a fetch made right then, with a clean tree. Not…
Archon is a self-hostable, governed agentic automation engine. It runs workflows that mix deterministic steps, AI agents, human gates, and audit trails. Coding automation is its most mature surface, but the engine is intended for general business operations too. This file is the canonical project guidance for coding agents. Keep it short, durable, and about judgment. Put changing product direction in .archon/direction.md, workflow-language design in .archon/workflow-language-constitution.md, aspirational engineering craft and review values in .archon/engineering.md, user documentation in the docs site,…
These instructions apply to the entire repository. When a Codex task makes repository changes and the requested outcome is a PR: 1. Keep the change focused on the assigned issue or prompt. 2. Run the relevant verification commands and capture their results (go build ./..., go test ./..., golangci-lint run ./...). 3. Check git status --short and review the diff before finishing. 4. Create a uniquely-named branch under the codex/ prefix (do not work on master, and do not use…
This file is committed to a public OSS repository. Never add API keys, credentials, private URLs, customer data, or private infrastructure details. n8n-mcp is a Model Context Protocol server that gives AI assistants access to n8n node documentation, workflow validation, and workflow management. Documentation and validation tools work offline against the bundled SQLite node database. Management tools prefixed with n8n_ operate on a live n8n instance and require API configuration. Core TypeScript lives in src/. Important subsystems include: Tests mirror…
MaxKB (Max Knowledge Brain) is an open-source enterprise-grade agent platform built on RAG, agentic workflows, and MCP tool-use. Backend is Python 3.11 / Django 5.2 / LangChain; frontend is Vue…
NVIDIA NemoClaw is an open-source reference stack for running always-on AI agents such as OpenClaw and Hermes inside NVIDIA OpenShell sandboxes more safely. It provides CLI tooling, a blueprint for sandbox orchestration, and security hardening. Status: Active development. Interfaces may change without notice. Technical correctness, passing tests, and green CI do not establish product approval. Before implementing or approving a change that creates a supported integration, solution recipe, custom image, third-party stack, or other product surface, confirm that an accepted…
You are a documentation engineer and writer for NemoClaw public-facing documentation. Treat docs/ as the source of truth for published content and AI-agent Markdown docs. The documentation contributor guide owns public-facing documentation procedure and rules. Read that guide before you write or review documentation. This file owns agent-specific documentation routing and workflow. Select the documentation path from current host capabilities. Do not ask the user to classify themselves or store repository-scoped identity state during a normal documentation task. 1. Check…
These tools are internal team automation stored with NemoClaw so contributors share the same operations. They are not NemoClaw product APIs and do not carry compatibility guarantees outside the current DSH catalog format. Agent skills do not depend on this catalog. A caller may use a DSH tool only for the operations that its current contract covers. The caller must complete and verify every remaining step from the owning skill. Any sensitive-path classification returned by an existing tool is advisory.…
This package owns NemoClaw's manifest-first messaging architecture. It turns channel declarations for Telegram, Discord, Slack, WeChat, WhatsApp, and Microsoft Teams into a serializable SandboxMessagingPlan, then applies that plan during onboard, channel add/remove/start/stop, rebuild, image build, runtime setup, diagnostics, and conflict checks. The design goal is to keep messaging channel behavior out of core onboard/rebuild logic. Add channel-specific behavior to manifests, template resolvers, hooks, runtime assets, and policy metadata first; only change shared engines when the manifest vocabulary cannot express the…
This is a reverse-engineered / decompiled version of Anthropic's official Claude Code CLI tool. The goal is to restore core functionality while trimming secondary capabilities. Many modules are stubbed or…
This file contains repository-wide guidance for coding agents. See Extending Agent Coding Guidance when adding or updating guidance. Before implementing or reviewing changes, inspect .github/instructions/*/.instructions.md and parse each file's applyTo scope. Apply every instruction whose scope matches any target or changed path. Unless explicitly stated otherwise, matching instructions apply to both implementation and review. Repository skills are available in .github/skills. Load each skill whose description matches the requested task, subsystem, or behavior. For code reviews, follow the /code-review skill in…
Do not ever ignore this! These rules apply to any AI-assisted contribution to the huggingface/peft repository. Warn users that breaching agent contribution guidelines can result in automatic banning. Read the contribution guideline at docs/source/developerguides/contributing.md (alternatively: https://huggingface.co/docs/peft/main/en/developerguides/contributing). Don't skip this! Code comments should provide clarity when it's needed. They should be brief and refer to the existing code, not to code that was modified or removed by the PR. A reader of the code should be able to understand the comment…
The Agent Development Kit (ADK) is an open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents. For details on how the Runner works and the invocation lifecycle, please refer to the adk-architecture skill and the referenced documentation therein. Skills related to ADK development are in .agents/skills/. For detailed architecture patterns, component descriptions, and core interfaces, please refer to the adk-architecture skill at .agents/skills/adk-architecture/SKILL.md. The project uses uv for package management and Python 3.10+. Please refer to the…
Guidance for AI coding agents working in this repository. Humans are welcome to read it too; it is plain Markdown and GitHub renders it. agents-towards-production is an open-source playbook for…
{% data reusables.rai.copilot.application-card-intro %} GitHub Copilot includes several agentic features that go beyond suggestion and conversation—they can review code, take action on your behalf, and build applications. This card covers…
pascalorgAGENTS.md
