# qualixar-os - Doramagic AI Context Pack > Positioning: a pre-install experience and judgment asset. It helps the host AI get off to a good start, but it does not mean the project has already been installed, run, or validated. ## Sufficiency Principle - **Sufficiency over compression**: The AI Context Pack should be sufficient for the host AI to understand the project's value, capability boundaries, entrypoints, risks, and evidence sources before starting work; it may be layered, but it does not aim for the shortest possible summary. - **Compression policy**: Compress only noise and duplication, never context that affects judgment or the quality of the work. ## How the Host AI Should Use This You are reading the AI Context Pack that Doramagic compiled for qualixar-os. Treat it as pre-work context: help the user understand who it fits, what it can do, how to start, what must be verified after install, and where the risks are. Do not claim that you have already installed, run, or executed the target project. ## Claim Consumption Rules - **Fact source**: Repo Evidence + Claim/Evidence Graph; the Human Wiki only supplies salience, terminology, and narrative structure. - **Minimum status for a fact**: `supported` - `supported`: May be used as a project fact, but the answer must cite the claim_id and evidence path. - `weak`: Usable only as a low-confidence lead; the user must be asked to keep verifying. - `inferred`: Usable only for risk notes or open questions; must not be packaged as a project fact. - `unverified`: Must not be used as fact; state clearly that evidence is insufficient. - `contradicted`: Must show the conflicting sources and must not force a single version on the user's behalf. ## Who It Fits Best - **AI researchers or builders of research-oriented Agents**: The README clearly centers on research, experiment, or paper workflows. Evidence: `README.md` Claim: `clm_0004` supported 0.86 - **Developers already using host AIs such as Claude/Codex/Cursor/Gemini**: The README or plugin config mentions multiple host AIs. Evidence: `README.md` Claim: `clm_0005` supported 0.86 - **Users who want to bring professional workflows into a host AI**: The repo contains Skill documents. Evidence: `.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` et al. Claim: `clm_0006` supported 0.86 ## What It Can Do - **AI Skill / Agent Instruction Asset Library** (Previewable before install): The project contains Skill or Agent instruction files that a host AI can read, useful for bringing professional workflows into hosts like Claude, Codex, or Cursor. Evidence: `.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Multi-Host Install and Distribution** (Verify after install): The project contains plugin or marketplace configuration, indicating it targets install and distribution across one or more AI hosts. Evidence: `claude-code-plugin/plugin.json`, `packages/qos-claude-code/plugin.json`, `registry-listings/cursor-plugin.json`, `registry-listings/mcp-marketplace.json` Claim: `clm_0002` supported 0.86 - **Command-Line Startup or Install Flow** (Verify after install): The project documentation contains runnable commands; real use requires running them in a local or host environment. Evidence: `README.md`, `packages/qos-claude-code/README.md` Claim: `clm_0003` supported 0.86 ## How to Start - `npx qualixar-os` Evidence: `README.md` Claim: `clm_0007` supported 0.86 - `npm install -g qualixar-os` Evidence: `README.md` Claim: `clm_0008` supported 0.86 - `git clone https://github.com/qualixar/qualixar-os.git` Evidence: `README.md` Claim: `clm_0009` supported 0.86 - `npm install -g qos-claude-code` Evidence: `packages/qos-claude-code/README.md` Claim: `clm_0010` supported 0.86 ## Continue-or-Stop Decision Card - **Current recommendation**: Needs admin / security approval - **Why**: Continuing may involve secrets, accounts, external services, or sensitive context; get admin or security approval first. ### 30-Second Read - **What to do now**: Needs admin / security approval - **Minimum safe next step**: Run Prompt Preview first; if credentials or an enterprise environment are involved, get approval before trialing - **Do not trust yet**: Tool permission boundaries cannot be trusted before install. - **Continuing will touch**: Command execution, Host AI configuration, Local environment or project files ### What You Can Trust Now - **Target-audience signal: AI researchers or builders of research-oriented Agents** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0004` supported 0.86 - **Target-audience signal: Developers already using host AIs such as Claude/Codex/Cursor/Gemini** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0005` supported 0.86 - **Target-audience signal: Users who want to bring professional workflows into a host AI** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` et al. Claim: `clm_0006` supported 0.86 - **Capability exists: AI Skill / Agent Instruction Asset Library** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Capability exists: Multi-Host Install and Distribution** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `claude-code-plugin/plugin.json`, `packages/qos-claude-code/plugin.json`, `registry-listings/cursor-plugin.json`, `registry-listings/mcp-marketplace.json` Claim: `clm_0002` supported 0.86 - **Capability exists: Command-Line Startup or Install Flow** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `README.md`, `packages/qos-claude-code/README.md` Claim: `clm_0003` supported 0.86 ### What You Cannot Trust Yet - **Tool permission boundaries cannot be trusted before install.** (unverified): MCP/tool projects usually touch files, the network, the browser, or external APIs, so permissions and logs must be checked for real. - **Real output quality cannot be trusted before install.** (unverified): Prompt Preview can only show how it guides you; it cannot prove result quality in the real project. - **Host AI version compatibility cannot be trusted before install.** (unverified): Host loading rules and version differences across Claude, Cursor, Codex, Gemini, and others must be verified in a real environment. - **That it will not pollute your existing host AI's behavior cannot be trusted directly.** (inferred): Skill, plugin, and AGENTS/CLAUDE/GEMINI instructions may change the host AI's default behavior. Evidence: `.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` et al. - **Safe rollback cannot be assumed by default.** (unverified): Unless the project clearly provides uninstall and recovery instructions, verify in an isolated environment first. - **After a real install, is it compatible with the user's current host AI version?** (unverified): Compatibility can only be verified in the actual host environment. Evidence: `claude-code-plugin/plugin.json`, `packages/qos-claude-code/plugin.json`, `registry-listings/cursor-plugin.json`, `registry-listings/mcp-marketplace.json` - **Does the project's output quality meet the user's specific task?** (unverified): The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. - **Do the install commands require network access, permissions, or global writes?** (unverified): This affects install risk in both enterprise and personal environments. Evidence: `README.md` ### What Continuing Will Touch - **Command execution**: Package managers, network downloads, the local plugin directory, project config, or the user's home directory. Why: Running the very first command can already change your environment; decide whether it is worth running first. Evidence: `README.md`, `packages/qos-claude-code/README.md` - **Host AI configuration**: The plugin, Skill, or rule-loading config of hosts like Claude/Codex/Cursor/Gemini/OpenCode. Why: Host configuration changes how the AI works afterward and may conflict with the user's existing rules. Evidence: `.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` et al. - **Local environment or project files**: Install results, plugin caches, project config, or local dependency directories. Why: The write scope and rollback path cannot be proven before install and need isolated verification. Evidence: `README.md`, `claude-code-plugin/plugin.json`, `packages/qos-claude-code/README.md`, `packages/qos-claude-code/plugin.json` et al. - **Environment variables / API keys**: Project entry docs explicitly showing API key, token, secret, or account credential configuration. Why: If a real install needs credentials, use test credentials first and go through a permission/compliance review. Evidence: `README.md`, `adapters/claude_managed_types.py`, `deploy/README.md`, `deploy/azure-container-apps.md` et al. - **Host AI context**: The AI Context Pack, Prompt Preview, Skill routing, risk rules, and project facts. Why: Importing context affects the host AI's later judgment, so avoid packaging unverified items as facts. ### Minimum Safe Next Steps - **Run Prompt Preview first**: Use a pre-install interactive trial to judge whether the way of working fits; it needs no authorization or environment change. (applies when: Applies to any project, especially when output quality is unknown.) - **Trial-install only in an isolated directory or a test account**: Avoid letting install commands pollute your primary host AI, real projects, or home directory. (applies when: When there are signals of command execution, plugin config, or local writes.) - **Back up your host AI configuration first**: Skill, plugin, and rule files may change the default behavior of Claude/Cursor/Codex. (applies when: When there is a plugin manifest, a Skill, or a host rule entrypoint.) - **Do not use real production credentials**: Once an environment variable / API key enters the host or toolchain, it can create account and compliance risk. (applies when: When environment signals like API, TOKEN, KEY, or SECRET appear.) - **After install, verify just one minimal task**: Verify loading, compatibility, output quality, and rollback first, then decide whether to use it deeply. (applies when: When moving from a trial into a real workflow.) ### Exit Plan - **Preserve the pre-install state**: Record the original host config and project state so you can later judge whether it is recoverable. - **Be ready to remove the host plugin / Skill / rule entrypoint**: If behavior is off after the trial install, you can restore the host AI to its pre-trial state. - **Record the install commands and written paths**: Without clear uninstall instructions, you at least need to know which directories or configs to clean up manually. - **Be ready to revoke test API keys or tokens**: If test credentials leak or are misused, you can cut losses quickly. - **If there is no rollback path, do not enter your primary environment**: No rollback is a blocker before continuing; do not proceed on trust or luck. ## What Can Only Be Previewed - Explain who the project fits and what it can do - Demonstrate a typical conversation flow based on project docs - Help the user decide whether it is worth installing or researching further ## What Must Be Verified After Install - Actually installing the Skill, plugin, or CLI - Running scripts, modifying local files, or accessing external services - Verifying real output quality, performance, and compatibility ## Boundary & Risk Decision Card - **Mistaking the pre-install preview for a real run**: The user may overestimate how much configuration, permission, and compatibility verification the project has already done. Mitigation: Clearly separate prompt_preview_can_do from runtime_required. Claim: `clm_0011` inferred 0.45 - **Host AI plugin or Skill rule conflicts**: New rules may change how the user's existing host AI behaves. Mitigation: Inspect the plugin manifest and Skill files before installing, and test in isolation if needed. Evidence: `claude-code-plugin/plugin.json`, `packages/qos-claude-code/plugin.json`, `registry-listings/cursor-plugin.json`, `registry-listings/mcp-marketplace.json` Claim: `clm_0012` supported 0.86 - **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `README.md`, `packages/qos-claude-code/README.md` Claim: `clm_0013` supported 0.86 - **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment. - **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. - **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments. ## Pre-Work Working Context ### Loading Order - First read how_to_use.host_ai_instruction to establish the boundaries of this pre-install judgment asset. - Read claim_graph_summary to confirm facts come from the Claim/Evidence Graph, not the Human Wiki narrative. - Then read intended_users, capabilities, and quick_start_candidates to judge whether the user is a match. - When you need to carry out a concrete task, check role_skill_index first, then evidence_index. - For real install, file modification, network access, performance, or compatibility questions, turn to risk_card and boundaries.runtime_required. ### Task Routes - **AI Skill / Agent Instruction Asset Library**: Use role_skill_index / evidence_index to help the user pick a usable role, Skill, or workflow first. Boundary: Can be experienced via a pre-install Prompt. Evidence: `.claude/skills/gitnexus/gitnexus-cli/SKILL.md`, `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md`, `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md`, `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Multi-Host Install and Distribution**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `claude-code-plugin/plugin.json`, `packages/qos-claude-code/plugin.json`, `registry-listings/cursor-plugin.json`, `registry-listings/mcp-marketplace.json` Claim: `clm_0002` supported 0.86 - **Command-Line Startup or Install Flow**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `README.md`, `packages/qos-claude-code/README.md` Claim: `clm_0003` supported 0.86 ### Context Scale - Total files: 531 - Important-file coverage: 40/531 - Evidence index entries: 80 - Role / Skill entries: 6 ### Handling Insufficient Evidence - **missing_evidence**: State that evidence is insufficient and ask the user for the target file, a README section, or after-install verification records; do not fill in facts. - **out_of_scope_request**: State that the task is beyond the current AI Context Pack's evidence scope and suggest the user check the Human Manual or verify after a real install. - **runtime_request**: Provide a pre-install checklist and command sources, but do not run commands for the user or claim they have been run. - **source_conflict**: Show the conflicting sources side by side, mark them as unverified, and do not force a single version. ## Prompt Recipes ### Fit assessment - Goal: Judge whether this project fits the user's current task. - Expected output: A fit conclusion, key reasons, evidence citations, what can be previewed before install, what must be verified after install, and a next-step recommendation. ```text Based on the AI Context Pack for qualixar-os, ask me 3 necessary questions first, then judge whether it fits my task. The answer must cover: who it fits, what it can do, what it cannot do, whether it is worth installing, and where the evidence comes from. Every project fact must cite evidence_refs, source_paths, or a claim_id. ``` ### Pre-install experience - Goal: Let the user feel the core workflow before installing, while avoiding packaging the preview as real capability or a marketing promise. - Expected output: An experience script with boundary labels, an after-install verification checklist, and a cautious recommendation; with no real-run promises or strong marketing language. ```text Treat qualixar-os as a pre-install experience asset, not an already-installed tool or a real runtime environment. Output exactly four parts: 1. Ask me 3 necessary questions first. 2. Give an "experience script": use the three labels [Previewable before install], [Must verify after install], and [Insufficient evidence] to show how it might guide the workflow. 3. Give an after-install verification checklist: list which capabilities can only be confirmed after a real install, real host loading, and a real project run. 4. Give a cautious recommendation: only "worth researching/trialing further", "add information before deciding", or "not recommended to continue"; do not endorse the project. Hard boundaries: - Do not claim you have installed, run, executed tests, modified files, or produced real results. - Do not write promise-like phrasing such as "auto-adapts", "guarantees passing", "perfect fit", or "strongly recommend installing". - If you describe how it works after install, you must use a conditional such as "if installed successfully and the host loads the Skill correctly, it might...". - The experience script may only be written as "example lines / hypothetical flow": use "might ask / might suggest / might show", not "has written, has generated, has passed, is running, is generating". - Prompt Preview does not hand out install commands; if the user is ready to trial, only prompt them to read Quick Start and the Risk Card first and to verify in an isolated environment. - Every project fact must come from a supported claim, evidence_refs, or source_paths; inferred/unverified items can only be risks or open questions. ``` ### Role / Skill selection - Goal: Pick the best-matching asset from the project's roles or Skills. - Expected output: A list of candidate roles or Skills, each with an applicable scenario, evidence paths, risk boundary, and whether after-install verification is needed. ```text Read role_skill_index and recommend 3-5 of the most relevant roles or Skills for my target task. For each recommendation, state the applicable scenario, likely output, risk boundary, and evidence_refs. ``` ### Risk pre-check - Goal: Identify environment, permission, rule-conflict, and quality risks before installing or adopting. - Expected output: A checklist of environment, permission, dependency, license, host-conflict, quality risk, and unknown items. ```text Based on risk_card, boundaries, and quick_start_candidates, give me a pre-install risk pre-check list. Do not run commands for me; only explain what I should check, why, and what impact a failure would have. ``` ### Host AI kickoff instruction - Goal: Turn the project context into a host AI instruction for the start of a conversation. - Expected output: A pre-work instruction with clear boundaries and clear evidence citations, suitable to copy to a host AI. ```text Based on the AI Context Pack for qualixar-os, generate a pre-work instruction I can paste to my host AI. This instruction must obey not_runtime=true and must not claim the project has been installed, run, or produced real results. ``` ## Role / Skill Index - Indexed 6 role / Skill / project-doc entries. - **gitnexus-cli** (skill): Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\ Activation hint: When the user's task is highly relevant to the workflow described by “gitnexus-cli”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/gitnexus/gitnexus-cli/SKILL.md` - **gitnexus-debugging** (skill): Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: \"Why is X failing?\", \"Where does this error come from?\", \"Trace this bug\ Activation hint: When the user's task is highly relevant to the workflow described by “gitnexus-debugging”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md` - **gitnexus-exploring** (skill): Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: \"How does X work?\", \"What calls this function?\", \"Show me the auth flow\ Activation hint: When the user's task is highly relevant to the workflow described by “gitnexus-exploring”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md` - **gitnexus-guide** (skill): Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: \"What GitNexus tools are available?\", \"How do I use GitNexus?\ Activation hint: When the user's task is highly relevant to the workflow described by “gitnexus-guide”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` - **gitnexus-impact-analysis** (skill): Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: \"Is it safe to change X?\", \"What depends on this?\", \"What will break?\ Activation hint: When the user's task is highly relevant to the workflow described by “gitnexus-impact-analysis”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/gitnexus/gitnexus-impact-analysis/SKILL.md` - **gitnexus-refactoring** (skill): Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: \"Rename this function\", \"Extract this into a module\", \"Refactor this class\", \"Move this to a separate file\ Activation hint: When the user's task is highly relevant to the workflow described by “gitnexus-refactoring”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/gitnexus/gitnexus-refactoring/SKILL.md` ## Evidence Index - Indexed 80 evidence entries. - **Qualixar OS** (documentation): ! License: FSL-1.1 https://img.shields.io/badge/License-FSL--1.1-blue.svg https://fsl.software ! Tests: 2,936 passing https://img.shields.io/badge/Tests-2%2C936 passing-brightgreen https://github.com/qualixar/qualixar-os ! TypeScript https://img.shields.io/badge/TypeScript-5.7-3178C6?logo=typescript&logoColor=white https://www.typescriptlang.org/ ! Node.js 22+ https://img.shields.io/badge/Node.js-22%2B-339933?logo=node.js&logoColor=white https://nodejs.org/ ! arXiv https://img.shields.io/badge/arXiv-2604.06392-b31b1b https://arxiv.org/abs/2604.06392 ! DOI https://img.shields.io/badge/DOI-10.5281%2Fzenodo.19454219-blue https://doi.org/10.5281/zenodo.19454219 Evidence: `README.md` - **Qualixar OS Python Adapters** (documentation): Python client and framework adapters for the Qualixar OS agent operating system. Evidence: `adapters/README.md` - **Qualixar OS — Claude Code Plugin** (documentation): The Universal OS for AI Agents, integrated into Claude Code. Evidence: `claude-code-plugin/README.md` - **Qualixar OS Deployment Guide** (documentation): Platform Complexity Cost Best For ---------- ----------- ------ ---------- Docker Compose ../docker-compose.yml Low Free local Development, self-hosted Fly.io ./fly-io.md Low Free tier available Quick public deploy Railway ./railway.md Lowest Free tier available 1-click deploy Azure Container Apps ./azure-container-apps.md Medium Pay-as-you-go Enterprise, scaling Kubernetes ./kubernetes.md High Varies Large-scale production Evidence: `deploy/README.md` - **Agents Tab** (documentation): The Agents tab shows all registered agents in the system. Each agent has a role, an assigned model, tool permissions, and execution history. Evidence: `docs/dashboard/agents.md` - **QOS Claude Code Plugin** (documentation): Integrates Qualixar OS with Claude Code CLI for native agent orchestration. Evidence: `packages/qos-claude-code/README.md` - **Package** (package_manifest): { "name": "@qualixar-os/dashboard", "private": true, "version": "2.0.0", "type": "module", "scripts": { "dev": "vite", "build": "vite build", "preview": "vite preview" }, "dependencies": { "d3": "^7.9.0", "d3-force": "^3.0.0", "framer-motion": "^12.0.0", "lucide-react": "^1.7.0", "react": "^19.0.0", "react-dom": "^19.0.0", "recharts": "^2.15.0", "zustand": "^5.0.0" }, "devDependencies": { "@types/d3": "^7.4.0", "@types/react": "^19.0.0", "@types/react-dom": "^19.0.0", "@vitejs/plugin-react": "^4.3.0", "tailwindcss": "^4.0.0", "vite": "^6.2.0" } } Evidence: `dashboard/package.json` - **Package** (package_manifest): { "name": "qualixar-os", "version": "2.2.3", "description": "Qualixar OS: The Universal OS for AI Agents. One platform, every model, every framework, every transport.", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "exports": { ".": { "import": "./dist/index.js", "types": "./dist/index.d.ts" } }, "files": "dist", "bin", "README.md", "LICENSE", "scripts" , "bin": { "qos": "./bin/qos.js", "qualixar-os": "./bin/qos.js" }, "scripts": { "build": "tsc && npm run build:dashboard", "build:dashboard": "cd dashboard && npm run build", "dev": "tsx src/channels/cli.ts", "test": "vitest run", "test:watch": "vitest", "test:coverage": "vitest run --coverage", "test:e2e": "vite… Evidence: `package.json` - **Package** (package_manifest): { "name": "create-qualixar-os", "version": "0.1.0", "description": "Create a new Qualixar OS project — The Universal Agent Orchestration Layer", "type": "module", "bin": { "create-qualixar-os": "./dist/index.js" }, "files": "dist" , "scripts": { "build": "tsc", "dev": "tsx src/index.ts", "test": "vitest run", "test:watch": "vitest" }, "dependencies": { "@clack/prompts": "^0.9.0", "chalk": "^5.4.0", "yaml": "^2.7.0" }, "devDependencies": { "typescript": "^5.7.0", "tsx": "^4.19.0", "vitest": "^3.0.0", "@types/node": "^22.0.0" }, "engines": { "node": " =22.0.0" }, "keywords": "qos", "qualixar", "agent", "orchestration", "mcp", "ai" , "license": "MIT" } Evidence: `packages/create-qos/package.json` - **Package** (package_manifest): { "name": "qos-claude-code", "version": "2.1.1", "description": "Claude Code plugin for Qualixar OS — submit tasks, browse workspaces, manage agents", "keywords": "qualixar-os", "claude-code", "ai-agents", "orchestration", "qos-compatible", "openclaw", "claw-compatible" , "license": "FSL-1.1-ALv2", "author": "qualixar", "repository": { "type": "git", "url": "https://github.com/qualixar/qualixar-os" }, "homepage": "https://qualixar.com", "files": "plugin.json", "commands/", "skills/", "agents/", "README.md" } Evidence: `packages/qos-claude-code/package.json` - **Getting Started with Qualixar OS** (documentation): Qualixar OS is the Universal OS for AI Agents. One control plane to orchestrate LLM agents across 15+ providers, 13 topologies, and every major IDE and framework. Evidence: `docs/getting-started.md` - **Build Your First AI Agent Team in 5 Minutes** (documentation): Build Your First AI Agent Team in 5 Minutes Evidence: `docs/guides/quickstart-5-minutes.md` - **Contributing to Qualixar OS** (documentation): Thank you for considering contributing to Qualixar OS! This guide will help you get started. Evidence: `CONTRIBUTING.md` - **GitNexus CLI Commands** (skill_instruction): All commands work via npx — no global install required. Evidence: `.claude/skills/gitnexus/gitnexus-cli/SKILL.md` - **Debugging with GitNexus** (skill_instruction): - "Why is this function failing?" - "Trace where this error comes from" - "Who calls this method?" - "This endpoint returns 500" - Investigating bugs, errors, or unexpected behavior Evidence: `.claude/skills/gitnexus/gitnexus-debugging/SKILL.md` - **Exploring Codebases with GitNexus** (skill_instruction): - "How does authentication work?" - "What's the project structure?" - "Show me the main components" - "Where is the database logic?" - Understanding code you haven't seen before Evidence: `.claude/skills/gitnexus/gitnexus-exploring/SKILL.md` - **GitNexus Guide** (skill_instruction): Quick reference for all GitNexus MCP tools, resources, and the knowledge graph schema. Evidence: `.claude/skills/gitnexus/gitnexus-guide/SKILL.md` - **Impact Analysis with GitNexus** (skill_instruction): - "Is it safe to change this function?" - "What will break if I modify X?" - "Show me the blast radius" - "Who uses this code?" - Before making non-trivial code changes - Before committing — to understand what your changes affect Evidence: `.claude/skills/gitnexus/gitnexus-impact-analysis/SKILL.md` - **Refactoring with GitNexus** (skill_instruction): - "Rename this function safely" - "Extract this into a module" - "Split this service" - "Move this to a new file" - Any task involving renaming, extracting, splitting, or restructuring code Evidence: `.claude/skills/gitnexus/gitnexus-refactoring/SKILL.md` - **Plugin** (structured_config): { "name": "qualixar-os", "displayName": "Qualixar OS", "version": "2.2.0", "description": "The Universal OS for AI Agents. Design multi-agent teams with Forge, browse skills, monitor costs, and integrate with Claude Code Agent Teams — all from Claude Code.", "author": "qualixar", "license": "FSL-1.1-ALv2", "homepage": "https://qualixar.com", "repository": "https://github.com/qualixar/qualixar-os", "provides": { "skills": "skills/forge-design.md", "skills/code-review.md", "skills/research.md", "skills/marketplace.md", "skills/agent-teams.md", "skills/task-orchestrator.md" , "hooks": { "PreToolUse": "hooks/cost-tracker.sh" , "PostToolUse": "hooks/cost-tracker.sh", "hooks/audit-log.sh" , "Team… Evidence: `claude-code-plugin/plugin.json` - **Plugin** (structured_config): { "name": "qos-claude-code", "displayName": "QOS Claude Code", "version": "2.1.1", "description": "Claude Code plugin for Qualixar OS — submit tasks, design agent teams with Forge, browse workspaces, and manage the skill marketplace.", "author": "qualixar", "license": "FSL-1.1-ALv2", "homepage": "https://qualixar.com", "repository": "https://github.com/qualixar/qualixar-os", "provides": { "skills": "skills/task-orchestrator.md" , "commands": "commands/qos-task.md", "commands/qos-forge.md", "commands/qos-status.md", "commands/qos-workspace.md", "commands/qos-marketplace.md" , "agents": { "name": "qos-orchestrator", "description": "Manages Qualixar OS tasks — submit, monitor, and inspect agen… Evidence: `packages/qos-claude-code/plugin.json` - **Functional Source License, Version 1.1, ALv2 Future License** (source_file): Functional Source License, Version 1.1, ALv2 Future License Evidence: `LICENSE` - **CLI Native Bridge** (documentation): The qos-claude-code plugin v2.1.1 connects Claude Code to Qualixar OS through two channels: MCP tools for structured LLM interaction, and native CLI commands via Bash for operations that MCP does not cover. This dual approach gives Claude Code complete access to every QOS capability. Evidence: `docs/claude-cli/cli-native-bridge.md` - **MCP Setup for Claude Code** (documentation): Qualixar OS exposes its full API as an MCP Model Context Protocol server. This lets Claude Code call QOS tools directly — run tasks, design teams, manage agents, and more — all through the standard MCP protocol over stdio transport. Evidence: `docs/claude-cli/mcp-setup.md` - **Qualixar OS for Claude Code CLI** (documentation): Qualixar OS integrates directly with Claude Code CLI through a native plugin qos-claude-code v2.1.1 . This gives you multi-agent orchestration, automatic team design, a skill marketplace, and full task lifecycle management without leaving your terminal. Evidence: `docs/claude-cli/overview.md` - **Installing the QOS Claude Code Plugin** (documentation): Installing the QOS Claude Code Plugin Evidence: `docs/claude-cli/plugin-install.md` - **Power User Guide — Claude Code + QOS** (documentation): Power User Guide — Claude Code + QOS Evidence: `docs/claude-cli/power-user.md` - **Using QOS Skills in Claude Code** (documentation): Skills are reusable, structured capabilities that Claude Code can invoke. The QOS plugin ships with the qos-task-orchestrator skill, which gives Claude Code structured knowledge of the entire QOS API for task management. Evidence: `docs/claude-cli/skills-guide.md` - **CLI vs MCP Access** (documentation): Qualixar OS exposes its capabilities through multiple transports. The two most relevant for Claude Code users are the CLI direct shell commands and the MCP server tool calls over stdio . They overlap significantly but are not identical. Evidence: `docs/cli/cli-vs-mcp.md` - **CLI Reference** (documentation): Qualixar OS ships a qos CLI binary built with Commander.js. It exposes 25 commands across 7 groups, plus access to the full 25-command Universal Command Protocol UCP via qos cmd and qos dispatch . Evidence: `docs/cli/overview.md` - **Audit Tab** (documentation): The Audit tab is an enterprise-grade audit log viewer. It records every security-relevant action in the system -- logins, data changes, permission modifications, exports, and more. Use it to investigate incidents, satisfy compliance requirements, or simply understand who did what and when. Evidence: `docs/dashboard/audit.md` - **Blueprints Tab** (documentation): The Blueprints tab is a gallery of reusable templates. Instead of configuring agents, topologies, workflows, or pipelines from scratch every time, you save them as blueprints and deploy them with one click. Evidence: `docs/dashboard/blueprints.md` - **Brain Tab** (documentation): The Brain tab is your prompt library. It stores, organizes, and versions every prompt used across the system -- system prompts, task templates, few-shot examples, and judge prompts. It also includes a judge configuration panel for controlling how quality evaluators behave. Evidence: `docs/dashboard/brain.md` - **Builder Tab — Workflow Builder** (documentation): The Builder tab provides a visual drag-and-drop interface for constructing agent workflows. Unlike Forge which auto-designs teams , Builder gives you full manual control over every node and connection. Evidence: `docs/dashboard/builder.md` - **Chat Tab** (documentation): The Chat tab provides an interactive conversation interface for working with your configured LLM models. It supports streaming responses, tool calling, conversation history, and multi-model switching. Evidence: `docs/dashboard/chat.md` - **Connectors Tab** (documentation): The Connectors tab is where you manage all external service integrations that Qualixar OS communicates with. This includes MCP Model Context Protocol servers, REST APIs, and webhooks. Each connector exposes a set of tools that agents can use during task execution. Evidence: `docs/dashboard/connectors.md` - **Cost Management Tab** (documentation): The Cost tab gives you full visibility into LLM spending. Every API call is tracked with token counts and estimated cost, broken down by provider, model, task, and agent. Evidence: `docs/dashboard/cost.md` - **Datasets Tab** (documentation): The Datasets tab lets you manage test and evaluation datasets used for agent benchmarking. You can upload data files, browse what is loaded, preview row-level content, and delete datasets you no longer need. Evidence: `docs/dashboard/datasets.md` - **Flows Tab** (documentation): The Flows tab is a visual editor for designing multi-agent execution flows. You define which agents participate, how they connect, and which topology governs their communication -- then run the entire flow from the dashboard. Evidence: `docs/dashboard/flows.md` - **Forge Tab — Team Designer** (documentation): The Forge tab is Qualixar OS's visual team designer. It lets you compose multi-agent teams by defining agent roles, selecting topologies, and configuring how agents communicate. Evidence: `docs/dashboard/forge.md` - **Gate Tab** (documentation): The Gate tab is a human-in-the-loop review system. When agents produce outputs that require human sign-off before execution, those outputs appear here as review items. You can approve, reject, or request revisions -- with optional feedback sent back to the agent. Evidence: `docs/dashboard/gate.md` - **Judges Tab** (documentation): The Judges tab shows how your agent outputs are being evaluated. Every time a task completes, one or more judge models review the output and issue a verdict. This tab gives you full visibility into those evaluations --- scores, verdicts, detailed feedback, and identified issues. Evidence: `docs/dashboard/judges.md` - **Lab Tab** (documentation): The Lab tab is your experimentation workspace. It lets you run A/B comparisons between two configurations --- different models, topologies, prompts, or parameter settings --- and see the results side by side with charts and metrics. Evidence: `docs/dashboard/lab.md` - **Logs Tab** (documentation): The Logs tab is a structured log viewer that displays system activity in a terminal-style stream. You can filter by log level and source, search for specific messages, and click any entry to see its full detail. Evidence: `docs/dashboard/logs.md` - **Marketplace Tab** (documentation): The Marketplace tab lets you extend Qualixar OS with community-built plugins, tools, and skills. Browse the catalog, install with one click, and manage installed extensions. Evidence: `docs/dashboard/marketplace.md` - **Memory Tab** (documentation): The Memory tab manages Qualixar OS's built-in RAG Retrieval-Augmented Generation memory system. Agents can store knowledge during execution and retrieve it in future tasks, enabling persistent context across sessions. Evidence: `docs/dashboard/memory.md` - **Dashboard Overview** (documentation): The Qualixar OS dashboard is a browser-based control center at http://localhost:3000 . It provides 24 tabs that cover every aspect of agent orchestration, from task management to cost tracking. Evidence: `docs/dashboard/overview.md` - **Pipelines Tab** (documentation): The Pipelines tab gives you a visual overview of where every task sits in the execution pipeline. Each task progresses through seven stages from submission to final output, and this tab shows that progression at a glance. Evidence: `docs/dashboard/pipelines.md` - **Settings Tab** (documentation): The Settings tab provides a UI for managing system configuration. Changes made here are written to ~/.qualixar-os/config.yaml and take effect immediately no restart required . Evidence: `docs/dashboard/settings.md` - **Swarms Tab** (documentation): The Swarms tab provides a live visualization of how your agents are organized and communicating during multi-agent tasks. It shows the active topology, which agents are running, and a log of all swarm events. Evidence: `docs/dashboard/swarms.md` - **Tools Tab** (documentation): The Tools tab manages all tools available to agents. Tools are organized into 6 categories and can be enabled, disabled, or configured per agent or globally. Evidence: `docs/dashboard/tools.md` - **Traces Tab** (documentation): The Traces tab is your observability window into what happens inside every request. It shows distributed traces --- end-to-end records of how a request flows through authentication, pipeline resolution, tool invocation, judging, and response serialization --- with precise timing for every step. Evidence: `docs/dashboard/traces.md` - **Vectors Tab** (documentation): The Vectors tab is a browser for your vector store and a semantic search playground. It shows store-level statistics, lets you search vectors by meaning not just keywords , and provides a detail view for inspecting individual entries with their content, metadata, and embedding dimensions. Evidence: `docs/dashboard/vectors.md` - **AutoGen Integration** (documentation): The AutoGen adapter wraps Qualixar OS as a callable tool compatible with AutoGen's function-calling protocol. The adapter is a plain Python dataclass -- no framework dependency required. It implements call so AutoGen can invoke it directly as a function tool. Evidence: `docs/frameworks/autogen.md` - **CrewAI Integration** (documentation): The CrewAI adapter wraps Qualixar OS as a CrewAIBaseTool that any CrewAI agent can use. When a crew member invokes the tool, Qualixar OS orchestrates a sub-team behind the scenes -- selecting models, topologies, and tools -- and returns the output to your crew pipeline. Evidence: `docs/frameworks/crewai.md` - **Custom Integration** (documentation): Qualixar OS exposes a REST API that works from any language or framework. This guide covers three approaches: the Python client, direct HTTP with curl, and building your own adapter. Evidence: `docs/frameworks/custom-integration.md` - **LangChain Integration** (documentation): The LangChain adapter wraps Qualixar OS as a BaseTool that any LangChain agent can invoke. Your agent describes a task in natural language, and Qualixar OS handles orchestration, model routing, cost tracking, and output delivery. Evidence: `docs/frameworks/langchain.md` - **Google ADK Integration** (documentation): The ADK adapter wraps Qualixar OS as a Google ADK FunctionTool . It exposes a plain Python function run qos task that ADK agents can call. Each invocation creates a short-lived HTTP client, submits the task, and returns the output string. Evidence: `docs/frameworks/openai-agents.md` - **Framework Integrations** (documentation): Qualixar OS provides Python adapters that connect it to popular AI agent frameworks. Each adapter wraps the Qualixar OS REST API as a native tool for the target framework, so you can use Qualixar OS capabilities -- Forge team design, 13 execution topologies, cost tracking, judge pipelines, and the skill marketplace -- from within the framework you already use. Evidence: `docs/frameworks/overview.md` - **Semantic Kernel Integration** (documentation): Qualixar OS does not yet ship a dedicated Semantic Kernel adapter. However, the Qualixar OS REST API works with any HTTP-capable framework. This page shows how to integrate Qualixar OS into a Semantic Kernel application using the HTTP API directly. Evidence: `docs/frameworks/semantic-kernel.md` - The remaining 20 evidence entries are in `AI_CONTEXT_PACK.json` or `EVIDENCE_INDEX.json`. ## Rules the Host AI Must Follow - **Treat this asset as pre-work context, not a runtime environment.**: The AI Context Pack contains only an evidence-backed understanding of the project, not the project's executable state. Evidence: `README.md`, `adapters/README.md`, `claude-code-plugin/README.md` - **When answering the user, distinguish what can be previewed from what can only be verified after install.**: The consumer value of the pre-install experience comes from reducing bad installs and misjudgments, not from pretending to be a real run. Evidence: `README.md`, `adapters/README.md`, `claude-code-plugin/README.md` ## Questions the User Should Answer First - Which host AI or local environment do you plan to use it in? - Do you just want to experience the workflow first, or are you ready to actually install? - What matters most to you: install cost, output quality, or conflicts with your existing rules? ## Acceptance Checks - Every capability claim can be traced back to a file path in evidence_refs. - AI_CONTEXT_PACK.md does not package previews as a real run. - The user can understand who it fits, what it can do, how to start, and the risk boundaries within 3 minutes. --- ## Doramagic Context Augmentation The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints. ## Human Manual Outline Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph. Host AI hard rules: - Do not treat page titles, section order, summaries, or importance values as factual project evidence. - When explaining the Human Manual outline, state that it is only a reading route or salience signal. - Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph. - **Overview, Installation & Key Concepts**: importance `high` - source_paths: README.md, docs/getting-started.md, docs/guides/quickstart-5-minutes.md, package.json, src/index.ts - **Core Runtime, Orchestration & Execution Pipeline**: importance `high` - source_paths: src/engine/orchestrator.ts, src/engine/auto-orchestrator.ts, src/engine/orchestrator-types.ts, src/engine/orchestrator-helpers.ts, src/engine/mode-engine.ts - **Memory, Quality, Routing & AI Provider Integration**: importance `high` - source_paths: src/memory/index.ts, src/memory/store.ts, src/memory/team-memory.ts, src/memory/embeddings.ts, src/memory/belief-graph.ts - **Dashboard, CLI, Marketplace, Builder & Protocol Extensibility**: importance `high` - source_paths: src/dashboard/app/App.tsx, src/dashboard/app/main.tsx, src/dashboard/app/store.ts, src/dashboard/app/types.ts, src/dashboard/app/tabs/OverviewTab.tsx ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `eee934b5942bfff2fa5543a39e64a78905640a0c` - inspected_files: `Dockerfile`, `README.md`, `docker-compose.yml`, `package.json`, `docs/claude-cli/cli-native-bridge.md`, `docs/claude-cli/mcp-setup.md`, `docs/claude-cli/overview.md`, `docs/claude-cli/plugin-install.md`, `docs/claude-cli/power-user.md`, `docs/claude-cli/skills-guide.md`, `docs/cli/cli-vs-mcp.md`, `docs/cli/overview.md`, `docs/dashboard/agents.md`, `docs/dashboard/audit.md`, `docs/dashboard/blueprints.md`, `docs/dashboard/brain.md`, `docs/dashboard/builder.md`, `docs/dashboard/chat.md`, `docs/dashboard/connectors.md`, `docs/dashboard/cost.md` Host AI hard rules: - Without repo_clone_verified=true, do not claim that the source code has been read. - Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts. - Without quick_start_verified=true, do not claim that the Quick Start path has run successfully. ## Doramagic Pitfall Constraints These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes. ### Constraint 1: Capability evidence risk requires verification - Trigger: README/documentation is current enough for a first validation pass. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: capability.assumptions | https://github.com/qualixar/qualixar-os - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 2: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: downstream_validation.risk_items | https://github.com/qualixar/qualixar-os - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 3: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: risks.scoring_risks | https://github.com/qualixar/qualixar-os - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 4: Maintenance risk requires verification - Trigger: issue_or_pr_quality=unknown。 - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/qualixar/qualixar-os - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 5: Maintenance risk requires verification - Trigger: release_recency=unknown。 - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/qualixar/qualixar-os - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.