Skip to content
Back to search

Jarvis-x-Atlas-Agents

Jarvis x Atlas Agents — Multi-Agent Engineering OS, Custom JSON-RPC 2.0 MCP Servers, 57-Skill Progressive Routing, Verify-Gated Harness, Lean Memory & Offline Evals

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/sonness1304--jarvis-x-atlas-agents/badge.svg)](/listings/sonness1304--jarvis-x-atlas-agents)

HTML

<a href="/listings/sonness1304--jarvis-x-atlas-agents"><img src="/api/listings/sonness1304--jarvis-x-atlas-agents/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Step 1 — Clone & Verify Locally (Zero `npm install`)

git clone https://github.com/Sonness1304/Jarvis-x-Atlas-Agents.git
cd Jarvis-x-Atlas-Agents

# Optional: install `jarvis` CLI globally on your PATH
npm link

# Verify all 6 engineering pillars, 20 tests, 6 offline eval suites & 0 privacy leaks
npm run doctor
npm test
npm run eval
npm run audit:privacy

Step 2 — Bootstrap Jarvis × Atlas Into Any Existing Project (1 Command)

node src/cli.mjs init --target ../my-project

This safely scaffolds `AGENTS.md`, `docs/project-checkpoint.md`, `.jarvis/mcp-config.example.toml`, and all **14 core skills** under `../my-project/.agents/skills/` without overwriting existing files. Verify immediately with:

node src/cli.mjs doctor --root ../my-project

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 284 lines
  1. # Jarvis × Atlas Agents — Multi-Agent Engineering OS & MCP Platform
  2. [![Node.js >= 20](https://img.shields.io/badge/Node.js-%3E%3D20%20ESM-0F5C54?style=flat-square)](https://nodejs.org/)
  3. [![Dependencies](https://img.shields.io/badge/Runtime%20Dependencies-Zero%20External-166534?style=flat-square)](#runnable-source-architecture-src)
  4. [![MCP Protocol](https://img.shields.io/badge/MCP-JSON--RPC%202.0%20(2025--06--18)-3730A3?style=flat-square)](docs/mcp-architecture.md)
  5. [![Skills System](https://img.shields.io/badge/Progressive%20Skills-14%20Bundled%20%7C%2057%20Catalog-B45309?style=flat-square)](docs/skills-catalog.md)
  6. [![Tests & Evals](https://img.shields.io/badge/Tests%2022%2F22%20%7C%20Evals%206%2F6-PASS-0F766E?style=flat-square)](docs/memory-and-evals.md)
  7. [![License: MIT](https://img.shields.io/badge/License-MIT-334155?style=flat-square)](LICENSE)
  8. > **A complete, clone-and-run Multi-Agent Engineering Operating System, custom Model Context Protocol (MCP) server suite, progressive 57-skill routing framework, verify-gated long-running harness, lean memory recovery controller, independent hybrid code review engine, and deterministic offline eval runner—implemented in zero-dependency Node.js ESM.**
  9. ---
  10. ## Table of Contents
  11. 1. [Why Jarvis × Atlas Exists](#why-jarvis--atlas-exists)
  12. 2. [System Architecture & Execution Flowcharts](#system-architecture--execution-flowcharts)
  13. 3. [Repository Structure (Full Downloadable Source)](#repository-structure-full-downloadable-source)
  14. 4. [Quickstart & Bootstrap Into Your Own Repo](#quickstart--bootstrap-into-your-own-repo)
  15. 5. [Unified CLI Reference (`jarvis`)](#unified-cli-reference-jarvis)
  16. 6. [Progressive Skills System (How It Works & Full Catalog)](#progressive-skills-system-how-it-works--full-catalog)
  17. 7. [Custom MCP Servers (Read-Only + Windows UIA-First)](#custom-mcp-servers-read-only--windows-uia-first)
  18. 8. [Measured Production Benchmarks](#measured-production-benchmarks)
  19. 9. [Deep-Dive Documentation & CV Brief](#deep-dive-documentation--cv-brief)
  20. ---
  21. ## Why Jarvis × Atlas Exists
  22. Most AI coding setups break down on real multi-session engineering work for five structural reasons:
  23. 1. **Prompt bloat & instruction drift** — dumping dozens of rules and skills into every turn wastes tokens and causes models to lose constraints after compaction.
  24. 2. **Optimistic "fake passes"** — agents claim tasks are done without real `exitCode === 0` checks, browser render proof, or anchored code reviews.
  25. 3. **Unsafe MCP & desktop boundaries** — unvalidated schemas, redirect/SSRF exposure, plaintext secrets in repo configs, or blind GUI click retries on `OUTCOME_UNKNOWN`.
  26. 4. **Multi-provider gateway protocol drops** — routing OpenAI Responses, Gemini, and Claude through a local proxy silently drops secondary `role: "developer"` instructions unless request translators append them cleanly.
  27. 5. **Broken cross-chat continuity** — long-running builds stall across fresh chat threads without a compact, machine-verified handoff packet and anti-drift task selector.
  28. **Jarvis × Atlas Agents** solves all five mechanically—in runnable code, not just prompt wishful thinking.
  29. ---
  30. ## System Architecture & Execution Flowcharts
  31. ### 1. Five-Tier Platform Architecture & Safety Invariants
  32. ![Jarvis x Atlas System Architecture](docs/diagrams/jarvis-atlas-architecture.svg)
  33. ### 2. End-to-End Task Execution Lifecycle Flowchart
  34. ![Jarvis x Atlas Execution Lifecycle Flowchart](docs/diagrams/jarvis-atlas-lifecycle.svg)
  35. ---
  36. ## Repository Structure (Full Downloadable Source)
  37. Everything below is included directly in this repository, runs out of the box with **Node.js `>= 20`** (`0` third-party npm packages), and is verified by automated tests:
  38. ```text
  39. Jarvis-x-Atlas-Agents/
  40. ├── src/ # 12 zero-dependency Node.js ESM core modules
  41. │ ├── cli.mjs # Unified `jarvis` CLI entrypoint (all 12 commands)
  42. │ ├── init-workspace.mjs # 1-command installer: scaffolds AGENTS.md, checkpoint, MCP & skills
  43. │ ├── doctor.mjs # 6-pillar workspace health & readiness diagnostic CLI
  44. │ ├── recovery.mjs # Lean Memory recovery (<= 8 KiB Hot Checkpoint, 20 KiB turn budget, SHA-256)
  45. │ ├── skills.mjs # Progressive Skill Registry & Intent Router (<= 8 entrypoints/turn)
  46. │ ├── task-context.mjs # Fail-closed readiness gate (--expected-task anti-drift, one-shot vs resume)
  47. │ ├── harness.mjs # Verify-gated long-running feature ledger & <= 2 KiB Markdown handoff
  48. │ ├── worktree.mjs # Isolated Git worktree manager for parallel lanes + dirty/main guards
  49. │ ├── review-engine.mjs # Independent Hybrid Review v2 (diff slicing, 100% coverage, existingCode anchors)
  50. │ ├── read-mcp.mjs # Custom JSON-RPC 2.0 Read-Only MCP server (github / telegram / discord)
  51. │ ├── windows-mcp-core.mjs # Custom JSON-RPC 2.0 Windows UIA-first MCP core (observe-before-act, anti-replay)
  52. │ └── eval-runner.mjs # Deterministic 6-suite offline eval runner (--save-baseline / --compare)
  53. ├── skills/ # 14 complete, installable SKILL.md playbooks (YAML frontmatter + gates)
  54. │ ├── using-superpowers/ # Cold-start <= 8 skill routing discipline
  55. │ ├── brainstorming/ # Spec-first design trade-offs
  56. │ ├── writing-plans/ # Snapshot-bound milestone breakdown
  57. │ ├── test-driven-development/ # Strict RED -> GREEN -> REFACTOR loop
  58. │ ├── systematic-debugging/ # 4-phase root-cause investigation
  59. │ ├── verification-before-completion/ # Fresh exit-code evidence gate
  60. │ ├── using-git-worktrees/ # Safe parallel branch isolation
  61. │ ├── orca-orchestration/ # <= 3 workers, depth <= 2, 1 writer/path, exact-SHA handoff
  62. │ ├── requesting-code-review/ # Hybrid Review v2 execution playbook
  63. │ ├── jarvis-ui-design/ # Responsive desktop/mobile/accessibility QA workflow
  64. │ ├── jarvis-diagram-design/ # Editorial #FAF9F5 SVG diagram engineering
  65. │ ├── jarvis-desktop/ # UIA-first + Native COM + anti-replay Windows protocol
  66. │ ├── jarvis-report-writing/ # Evidence-backed ADR & engineering report guide
  67. │ └── agent-security-hardening/ # Untrusted-data boundary, MCP least-privilege & secret audit
  68. ├── templates/ # Ready-to-use starter templates copied by `jarvis init`
  69. │ ├── AGENTS.md # Co-Lead governance contract (Jarvis x Atlas)
  70. │ ├── project-checkpoint.md # Hot Checkpoint starter (<= 8 KiB budget)
  71. │ └── mcp-config.toml # Host MCP registration config for Codex / OpenCode / Claude
  72. ├── docs/ # Deep-dive engineering guides & editable SVG diagrams
  73. │ ├── user-guide.md # Step-by-step installation, setup & daily CLI manual
  74. │ ├── how-it-works.md # Stage 0 -> Stage 5 lifecycle walkthrough
  75. │ ├── skills-catalog.md # Progressive skill architecture + full 57-skill ecosystem map
  76. │ ├── mcp-architecture.md # Deep dive: jarvis-read-mcp & jarvis-windows-mcp + threat model
  77. │ ├── memory-and-evals.md # <= 8 KiB memory tiering, Hybrid Review v2 & offline evals
  78. │ ├── cv-summary.md # Resume bullets (EN / VI) & technical interview talking points
  79. │ └── diagrams/ # Editorial SVG architecture & execution flowcharts
  80. ├── sdk/ # TypeScript SDK (strict MCP 2025-06-18 client & OS contracts)
  81. │ ├── types.ts # Shared TypeScript interfaces for MCP, Skills & Eval reports
  82. │ └── mcp-client.ts # Zero-dep TypeScript stdio JSON-RPC 2.0 MCP client
  83. ├── python/ # Python 3 MCP Client & Token-Budget / Eval Telemetry
  84. │ ├── jarvis_mcp_client.py # Zero-dep Python 3 stdio JSON-RPC 2.0 MCP client
  85. │ └── eval_analyzer.py # Token-budget & deterministic offline eval summary engine
  86. ├── ui/dashboard/ # Local zero-dep Mission Control Viewer (HTML + CSS)
  87. │ ├── index.html # Interactive skill explorer + Doctor/Eval JSON inspector
  88. │ └── styles.css # Editorial light-mode design system (#FAF9F5)
  89. ├── scripts/
  90. │ ├── privacy-audit.mjs # Pre-release PII, OS-path & secret-pattern scanner
  91. │ ├── windows/uia-bridge.ps1 # Windows UIA process-stamp & read-only control observer
  92. │ ├── windows/setup-env.ps1 # 1-click Windows environment check & test runner
  93. │ └── unix/bootstrap.sh # POSIX/macOS/Linux bootstrap & CI verification scripts
  94. ├── .github/workflows/ci.yml # Automated GitHub Actions CI (Node + TS + Python + Privacy)
  95. └── tests/ # 9 test suites (22 unit & polyglot integration tests)
  96. ```
  97. ---
  98. ## Quickstart & Bootstrap Into Your Own Repo
  99. ### Step 1 — Clone & Verify Locally (Zero `npm install`)
  100. ```bash
  101. git clone https://github.com/Sonness1304/Jarvis-x-Atlas-Agents.git
  102. cd Jarvis-x-Atlas-Agents
  103. # Optional: install `jarvis` CLI globally on your PATH
  104. npm link
  105. # Verify all 6 engineering pillars, 20 tests, 6 offline eval suites & 0 privacy leaks
  106. npm run doctor
  107. npm test
  108. npm run eval
  109. npm run audit:privacy
  110. ```
  111. ### Step 2 — Bootstrap Jarvis × Atlas Into Any Existing Project (1 Command)
  112. ```bash
  113. node src/cli.mjs init --target ../my-project
  114. ```
  115. This safely scaffolds `AGENTS.md`, `docs/project-checkpoint.md`, `.jarvis/mcp-config.example.toml`, and all **14 core skills** under `../my-project/.agents/skills/` without overwriting existing files. Verify immediately with:
  116. ```bash
  117. node src/cli.mjs doctor --root ../my-project
  118. ```
  119. ---
  120. ## Unified CLI Reference (`jarvis`)
  121. Run any subsystem via `node src/cli.mjs <command>` (or `jarvis <command>` after `npm link`):
  122. | Command | Subsystem | Example |
  123. |---|---|---|
  124. | `init` | Workspace Bootstrap | `node src/cli.mjs init --target ../my-app` |
  125. | `doctor` | 6-Pillar Health Check | `node src/cli.mjs doctor --root .` |
  126. | `recovery` | Lean Memory (`<= 8 KiB` + 20 KiB turn cap) | `node src/cli.mjs recovery brief --checkpoint templates/project-checkpoint.md` |
  127. | `skills` | Progressive Skill Router (`<= 8` / turn) | `node src/cli.mjs skills route "debug failing api test and review diff"` |
  128. | `context` | Fail-Closed Readiness & Anti-Drift Gate | `node src/cli.mjs context --checkpoint templates/project-checkpoint.md --expected-task TASK-001-bootstrap --intent "tdd"` |
  129. | `harness` | Verify-Gated Feature Ledger & `<= 2 KiB` Handoff | `node src/cli.mjs harness verify --dir ./sandbox --id F1` |
  130. | `worktree` | Isolated Parallel Git Worktrees | `node src/cli.mjs worktree create --repo . --name feat-auth` |
  131. | `review` | Independent Hybrid Review v2 | `node src/cli.mjs review slice --repo . --base HEAD~1` |
  132. | `mcp-read` | Read-Only JSON-RPC 2.0 MCP Server | `node src/cli.mjs mcp-read github` |
  133. | `mcp-windows` | Windows UIA-First JSON-RPC 2.0 MCP Core | `node src/cli.mjs mcp-windows` |
  134. | `eval` | 6-Suite Deterministic Offline Eval Runner | `node src/cli.mjs eval --save-baseline && node src/cli.mjs eval --compare` |
  135. | `audit` | Pre-Release PII & Secret Scanner | `node src/cli.mjs audit` |
  136. Full command walkthroughs and JSON examples are in **[`docs/user-guide.md`](docs/user-guide.md)**.
  137. ---
  138. ## Progressive Skills System (How It Works & Full Catalog)
  139. Instead of loading all **57 skills** into every prompt, **Jarvis × Atlas** reads only compact YAML frontmatter (`triggers`, `tags`, `description`) and loads **at most 8 matching `SKILL.md` playbooks per turn**—cutting skill context overhead by **65%–88%** while keeping domain rigor intact.
  140. ### Live Skill Routing Demo
  141. ```bash
  142. # Validate all 14 bundled SKILL.md playbooks
  143. node src/cli.mjs skills validate
  144. # Route a natural-language task to <= 8 playbooks with exact byte reduction report
  145. node src/cli.mjs skills route "build responsive dashboard ui, verify tests, and run hybrid code review"
  146. # Read a specific playbook
  147. node src/cli.mjs skills show orca-orchestration
  148. ```
  149. ### Bundled Core Playbooks (`skills/` — 14 Ready-to-Use Skills)
  150. | Domain | Bundled Playbooks | Production Ecosystem (57 Total) |
  151. |---|---|---|
  152. | **Core Governance & Planning** | `using-superpowers`, `brainstorming`, `writing-plans` | + `executing-plans`, `diagnosing-superpowers`, `domain-modeling`, `product-engineering-review`, `finishing-a-development-branch` |
  153. | **Engineering & Quality Gates** | `test-driven-development`, `systematic-debugging`, `verification-before-completion`, `requesting-code-review` | + `receiving-code-review`, `backend-patterns`, `ponytail*` (6 lean-code hygiene skills) |
  154. | **Multi-Agent Orchestration** | `using-git-worktrees`, `orca-orchestration` | + `dispatching-parallel-agents`, `subagent-driven-development`, `jarvis-mission` |
  155. | **UI/UX, Diagrams & Media** | `jarvis-ui-design`, `jarvis-diagram-design` | + `frontend-design`, `modern-web-guidance`, `jarvis-reference-build`, `anatomy`, `slide-studio`, `video-studio`, `playwright-cli`, Canva suite (6 skills) |
  156. | **Windows Automation & Security** | `jarvis-desktop`, `agent-security-hardening` | + `mcp-dependency-review`, `cli-anything` |
  157. | **Writing & Intelligence** | `jarvis-report-writing` | + `jarvis-scientific-research` *(177 selective LaTeX/academic skills)*, `humanizer`, `jarvis-last30days`, `jarvis-deepseek`, `agent-reach`, `jarvis-socratic-tutor`, `jarvis-work-search`, `jarvis-workday`, `jarvis-sherlock`, `jarvis-marketing`, `writing-for-agents`, `writing-skills` |
  158. See **[`docs/skills-catalog.md`](docs/skills-catalog.md)** for the full 57-skill map, scoring algorithm, and custom skill authoring guide.
  159. ---
  160. ## Custom MCP Servers (Read-Only + Windows UIA-First)
  161. Both servers implement **MCP `JSON-RPC 2.0` (`protocolVersion: 2025-06-18`)** over `stdio` with **zero external dependencies**:
  162. 1. **`src/read-mcp.mjs` (`github` | `telegram` | `discord`)**
  163. - Strict `additionalProperties: false` parameter schemas & `readOnlyHint: true` tool annotations.
  164. - Hardcoded trusted API origins, `redirect: "error"`, 8-second `AbortSignal` timeouts, env/OS-vault secret isolation, clamped text outputs (`<= 400` chars), and untrusted-data framing.
  165. 2. **`src/windows-mcp-core.mjs` (`jarvis-windows-mcp`)**
  166. - Control hierarchy: `API/CLI -> DOM -> Windows UIA -> Native COM fallback -> conditional vision`.
  167. - Enforces exact `PID + windowId + processStart` target binding, observe-before-act (`OBSERVE_BEFORE_ACT_REQUIRED`), SHA-256 driver integrity verification (`verifyDriverIntegrity`), per-call deadline watchdogs, and anti-replay blocking on `OUTCOME_UNKNOWN` until `windows_readback_state` resolves state.
  168. ```bash
  169. # Smoke test Read-Only GitHub MCP over stdio
  170. printf '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18"}}\n{"jsonrpc":"2.0","id":2,"method":"tools/list"}\n' | node src/cli.mjs mcp-read github
  171. # Smoke test Windows UIA-First MCP Core over stdio
  172. printf '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18"}}\n{"jsonrpc":"2.0","id":2,"method":"tools/list"}\n' | node src/cli.mjs mcp-windows
  173. ```
  174. Ready-to-paste host registration config: [`templates/mcp-config.toml`](templates/mcp-config.toml).
  175. ---
  176. ---
  177. ## Polyglot Architecture & Multi-Language Tooling
  178. Each language in this repository serves a real operational role—zero boilerplate, all verified in CI:
  179. | Layer | Language | Files | Purpose |
  180. |---|---|---|---|
  181. | **Agent OS Core & MCP Servers** | **JavaScript (Node.js ESM)** | `src/*.mjs` | Zero-dep CLI, JSON-RPC 2.0 MCP servers, Harness, Worktrees, Hybrid Review v2, Evals |
  182. | **Typed Client SDK** | **TypeScript** | `sdk/types.ts`, `sdk/mcp-client.ts` | Strongly typed MCP `2025-06-18` stdio client & report contracts |
  183. | **Python AI / Eval Integration** | **Python 3** | `python/jarvis_mcp_client.py`, `python/eval_analyzer.py` | Zero-dep Python MCP client + context token-budget & eval analyzer |
  184. | **Windows UIA Bridge & Setup** | **PowerShell** | `scripts/windows/uia-bridge.ps1`, `scripts/windows/setup-env.ps1` | Real Windows UIA `PID+HWND+processStart` observer + 1-click Windows setup |
  185. | **Mission Control Viewer** | **HTML / CSS** | `ui/dashboard/index.html`, `ui/dashboard/styles.css` | Local browser viewer for `doctor`, `eval`, and progressive `skills` JSON reports |
  186. | **Unix / CI Automation** | **Shell & YAML** | `scripts/unix/*.sh`, `.github/workflows/ci.yml` | Linux/macOS bootstrap & GitHub Actions quality gate |
  187. ```bash
  188. # Run Python 3 MCP client against local Node MCP servers
  189. python3 python/jarvis_mcp_client.py --server github
  190. python3 python/jarvis_mcp_client.py --server windows
  191. python3 python/eval_analyzer.py
  192. # Windows UIA read-only identity & visible-window observer
  193. pwsh -NoProfile -File scripts/windows/uia-bridge.ps1 -Action list-windows
  194. ```
  195. ---
  196. ## Measured Production Benchmarks
  197. | Engineering Subsystem | Production Workspace Metric | Included in This Repo |
  198. |---|---|---|
  199. | **Governance (`AGENTS.md`)** | `15.8 KB` combined global + repo, `0` duplicated shared blocks | [`templates/AGENTS.md`](templates/AGENTS.md) |
  200. | **Lean Memory Recovery** | **`<= 8 KiB`** Hot Checkpoint (`7.8 KiB` live), 20 KiB turn cap, SHA-256 provenance | [`src/recovery.mjs`](src/recovery.mjs) + [`src/task-context.mjs`](src/task-context.mjs) |
  201. | **Progressive Skills** | **57 skills** in production, capped at **`<= 8` entrypoints/turn** | [`src/skills.mjs`](src/skills.mjs) + **14 playbooks in [`skills/`](skills/)** |
  202. | **Long-Running Harness** | Verify-gated `exitCode === 0` rule + **`<= 2 KiB`** cross-session handoff | [`src/harness.mjs`](src/harness.mjs) + [`src/worktree.mjs`](src/worktree.mjs) |
  203. | **Independent Hybrid Review v2** | **100% changed-file coverage** + `existingCode` line anchors, zero gateway lock-in | [`src/review-engine.mjs`](src/review-engine.mjs) |
  204. | **Deterministic Offline Evals** | **`157/157` PASS (`passRate: 1.0`)** across 5 workspace suites; **`94/100`** Repo Audit | [`src/eval-runner.mjs`](src/eval-runner.mjs) (**6 suites, 20 tests PASS**) |
  205. | **Multi-Provider Gateway Patching** | Sealed SHA-256 `9router` manifest preserving multi-`developer` instructions across OpenAI Responses / Gemini / Claude | Documented in [`docs/how-it-works.md`](docs/how-it-works.md) |
  206. ---
  207. ## Deep-Dive Documentation & CV Brief
  208. - **[User Guide — Complete Installation & CLI Manual](docs/user-guide.md)**
  209. - **[How It Works — Stage-by-Stage Execution Walkthrough](docs/how-it-works.md)**
  210. - **[Skills Architecture & Complete 57-Skill Catalog](docs/skills-catalog.md)**
  211. - **[Custom MCP Architecture & Windows UIA Safety Model](docs/mcp-architecture.md)**
  212. - **[Lean Memory Tiering, Hybrid Review v2 & Deterministic Evals](docs/memory-and-evals.md)**
  213. - **[CV Project Summary & Technical Interview Talking Points (EN / VI)](docs/cv-summary.md)**
  214. ---
  215. ## Security, Privacy & License
  216. - **Strictly sanitized for public release:** verified by `npm run audit:privacy` (`0` personal paths, `0` private emails, `0` credentials/keys).
  217. - **Least-privilege by default:** external content is framed as untrusted data; destructive Git commands (`reset --hard`, `clean -fd`, force push) and external publish/deploy actions remain blocked behind explicit human approval.
  218. - Released under the [MIT License](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.