{
  "markdown": "<p align=\"right\"><a href=\"./README_CN.md\">🇨🇳 中文</a> · <a href=\"./README.es-ES.md\">Español</a></p>\n\n<p align=\"center\">\n  <img src=\"assets/banner-v2.png\" alt=\"AGI Super Team: an organized cross-harness team of agents and skills\" width=\"760\">\n</p>\n\n<h1 align=\"center\">🤖 AGI Super Team</h1>\n\n<p align=\"center\"><strong>An organized, installable team of Agents + Skills for local AI agent frameworks.</strong></p>\n\n<p align=\"center\">\n  Start with an outcome. Let the CEO route executives, executives dispatch specialists, Skills supply methods, and the Governor verify the result.\n</p>\n\nAGI Super Team is not a Codex-only plugin. It is a versioned, organized **Agents + Skills team system** for Claude Code, Codex, OpenClaw, Hermes, and other mainstream local AI agent frameworks through 18 explicit adapters.\n\nThe same organizational contract travels across frameworks: 14 top-level roles, 92 opt-in specialists, reusable Skills, eight outcome Teams, independent review, and explicit human approval.\n\nEach adapter maps that contract to the capabilities its target actually supports.\n\n<a id=\"coding-agent-quick-start\"></a>\n## ⚡ Quick Start for Coding Agents\n\nPaste this entire prompt into Claude Code, Codex, OpenClaw, or another coding agent. It authorizes installation only after a clean preview.\n\n```text\nInstall AGI Super Team from https://github.com/aAAaqwq/AGI-Super-Team into this coding-agent environment.\n\n1. Detect the current client and run `npx -y agi-super-team@latest --list-tools`.\n2. Choose exactly one matching adapter. Never use `--all-tools` for this installation.\n3. If this client supports native subagents, include `--all-subagents`; otherwise omit it and state the limitation.\n4. Run the selected command without `--install` first. Show the resolved package version, destinations, managed files, and conflicts.\n5. If the target is unambiguous and the preview is clean, run the same selection with `--install --connect`, then run a separate `--doctor` check.\n6. Stop instead of overwriting unmanaged files, using credentials, or guessing when the framework or destination is unclear.\n7. Report what was installed, whether native delegation is available, and whether I must restart or open a new task.\n```\n\nThis is one-prompt installation, not blind installation. Ambiguity, unsafe destinations, or conflicts still stop the workflow.\n\n## 🐝 Run your first swarm\n\nAfter installation, restart the client or open a new task. Start with this reusable prompt:\n\n```text\nSwarm agents: <your outcome>\n\nAct as the CEO coordinator.\n- Define the outcome and acceptance checks.\n- Choose the smallest sufficient team.\n- Parallelize only independent work with explicit file ownership.\n- Use Skills as methods and require an independent Governor review.\n- Synthesize one verified result.\n\nIf native multi-agent delegation is unavailable, execute the same role plan sequentially and say so. Do not publish, deploy, spend money, use credentials, or take irreversible action without my approval.\n```\n\n`Swarm agents:` is the routing cue, not a promise of unlimited parallelism. The installed framework controls actual concurrency, nesting, tools, and model access.\n\n<a id=\"install-into-your-agent-framework\"></a>\n## 🛠️ Manual CLI installation\n\nList all 18 adapter targets, preview one target, then apply the same selection:\n\n```bash\nnpx -y agi-super-team@latest --list-tools\nnpx -y agi-super-team@latest --tool claude-code\nnpx -y agi-super-team@latest --tool claude-code --install --connect\nnpx -y agi-super-team@latest --tool claude-code --doctor\n```\n\nThe commands above use the public npm package. For reproducible automation, replace `@latest` with an exact published version such as `@1.4.2`.\n\nThe npm distribution keeps all 817 `SKILL.md` entrypoints discoverable and includes the complete files for every Skill assigned by `config/team-manifest.json`. Browse the provenance-backed [Daniel's Original Skills](./skills/original/) collection for reviewed first-party work. Clone the repository when you need every auxiliary asset from the wider Skill library.\n\nReplace `claude-code` with an ID from `--list-tools`. Use `--all-tools` only when you intentionally want every global and project adapter. A no-argument run remains the legacy Codex preview; new automation should always name `--tool` or `--all-tools`.\n\n### Four primary frameworks\n\n| Platform | Preview command | Installed capability |\n|---|---|---|\n| **Claude Code** | `npx -y agi-super-team@latest --tool claude-code` | Native Markdown Agents + canonical Skills + Claude orchestrator |\n| **Codex** | `npx -y agi-super-team@latest --tool codex` | Main-session CEO + native TOML Agents + canonical Skills |\n| **OpenClaw** | `npx -y agi-super-team@latest --tool openclaw` | Namespaced Agent workspaces + canonical Skills + safe config merge |\n| **Hermes Agent** | `npx -y agi-super-team@latest --tool hermes` | Role Skills + canonical Skills + Profiles/Kanban blueprints |\n\n`--install` materializes files; `--install --connect` also writes a connection receipt. OpenClaw dry-runs and then upserts managed `agents.list` entries while preserving unmanaged Agents and creating no channel bindings. Claude and Codex use filesystem discovery. Hermes emits blueprints but does not create Profiles, Cron jobs, or a Gateway. See the [primary harness Adapter guide](./docs/guides/harness-adapters.md) for paths, permissions, and receipt requirements.\n\nOpenClaw `2026.7.1-2` requires Node.js `>=22.22.3 <23`, `>=24.15.0 <25`, or `>=25.9.0`. AGI Super Team itself still supports Node.js 18+, so this stricter prerequisite applies only when invoking the current OpenClaw CLI.\n\nClaude Code, Codex, OpenClaw, and Hermes are first-class entry points to the same team system, not separate editions with different organizations.\n\nDelivery format varies because each framework exposes different native Agent and Skill primitives.\n\n### Install executive subagent groups\n\nThe default remains the 14 top-level roles. Add one executive pyramid, or all 92 optional specialists:\n\n```bash\nnpx -y agi-super-team@latest --tool codex --with-subagents cto\nnpx -y agi-super-team@latest --tool codex --with-subagents cfo --with-subagents clo\nnpx -y agi-super-team@latest --tool codex --all-subagents --install\n```\n\nThe hierarchy is CEO → eleven manager executives → leaf specialists. CTO also references the existing canonical PE as delivery lead; it does not create a second PE identity. All 92 source files under `agents/*/subagents/*/AGENTS.md` are byte-for-byte copies from pinned `jnMetaCode/agency-agents-zh`; local routing and safety envelopes remain separate. CEO retains coordination authority, Governor remains an independent reviewer, and PE remains CTO's canonical delivery leaf rather than another manager. See [`config/agent-sources.lock.json`](./config/agent-sources.lock.json) for source URLs and SHA-256 digests. Nested Codex routing requires `max_depth = 2`; with four threads, run one manager plus at most two children per wave.\n\nThese are **18 AI client/runtime adapter targets**, not 18 interchangeable CLIs. An adapter can install native Agents, native Skills, project rules/context, or role packs degraded to Agent-as-Skill. File placement does not by itself prove that a current client loaded or executed the content.\n\n### All 18 adapter targets\n\nGlobal adapters normally resolve from the selected OS-home base; project adapters resolve from the selected project directory. OpenClaw and Hermes instead honor their native runtime roots, as shown below.\n\n| ID | Client/runtime | Scope | Agent delivery | Skill delivery | Status |\n|---|---|---|---|---|---|\n| `claude-code` | Claude Code | Global | Native Markdown Agent: `.claude/agents` | Canonical: `.claude/skills` | Structurally connected; runtime pending |\n| `codex` | Codex | Global | Main-session CEO + TOML: `.codex/agents` | Canonical: `.agents/skills` | Structurally connected; runtime pending |\n| `openclaw` | OpenClaw | Global | Native workspace: `<active config dir>/agency-agents/agi-super-team` | Canonical: `<active config dir>/skills/agi-super-team` | Structurally connected; runtime pending |\n| `hermes` | Hermes Agent | Global | Role Skills: `$HERMES_HOME/skills/agi-super-team-agents` | Canonical: `$HERMES_HOME/skills/agi-super-team` | Blueprint connected; runtime pending |\n| `copilot` | GitHub Copilot | Global | Markdown Agent: `.github/agents`, `.copilot/agents` | Native: `.copilot/skills` | Adapter |\n| `antigravity` | Antigravity | Global | Agent: `.gemini/config/agents` | Native: `.gemini/config/skills` | **Experimental** |\n| `gemini-cli` | Gemini CLI | Global | Markdown Agent: `.gemini/agents` | Native: `.gemini/skills` | Adapter |\n| `opencode` | OpenCode | Global | Markdown Agent: `.config/opencode/agents` | Native: `.config/opencode/skills` | Adapter |\n| `cursor` | Cursor | Global | Markdown Agent: `.cursor/agents` | Native: `.cursor/skills` | **Experimental** |\n| `trae` | Trae | Project | Project rule: `.trae/rules` | Native: `.trae/skills` | Project adapter |\n| `aider` | Aider | Project | Combined project rules: `CONVENTIONS.md` | Combined into the same project context | Project adapter |\n| `windsurf` | Windsurf | Project | Combined project rules: `.windsurfrules` | Combined into the same project context | Project adapter |\n| `qwen` | Qwen Code | Global | Markdown Agent: `.qwen/agents` | Native: `.qwen/skills` | Adapter |\n| `deerflow` | DeerFlow | Project | Agent-as-Skill: `skills/custom/agi-super-team-agents` | Native: `skills/custom/agi-super-team` | Project adapter |\n| `workbuddy` | WorkBuddy | Global | Agent-as-Skill: `.workbuddy/skills/agi-super-team-agents` | Native: `.workbuddy/skills/agi-super-team` | Adapter |\n| `codewhale` | CodeWhale | Global | Agent-as-Skill: `.codewhale/skills/agi-super-team-agents` | Native: `.codewhale/skills/agi-super-team` | Adapter |\n| `kiro` | Kiro | Global | Markdown Agent: `.kiro/agents` | Native: `.kiro/skills` | Adapter |\n| `qoder` | Qoder | Global | Markdown Agent: `.qoder/agents` | Native: `.qoder/skills` | Adapter |\n\nThe matrix describes the adapter contract in [`config/cli-adapters.json`](./config/cli-adapters.json), not a claim that all 18 clients have been runtime-verified. Cursor and Antigravity are explicitly experimental.\n\nUse the canonical [`orchestrate-agi-super-team`](./skills/orchestrate-agi-super-team/SKILL.md) Skill when a task needs the complete Team → C-suite → Skills/Subagents → Governor → CEO → human-approval flow. It detects the current framework's real delegation limits and records any flat or sequential fallback instead of pretending native nesting occurred.\n\n### Select destinations, refresh, and verify\n\nUse `--home` to redirect the OS-home base and `--project-dir` for project-scoped targets (the project directory defaults to the current directory). Hermes gives a non-empty `HERMES_HOME` precedence; OpenClaw follows `OPENCLAW_HOME`, `OPENCLAW_STATE_DIR`, and `OPENCLAW_CONFIG_PATH`. Combining `--home` with a conflicting runtime override fails before any write. This makes a disposable audit easy:\n\n```bash\nAGI_AUDIT_HOME=\"$(mktemp -d \"${TMPDIR:-/tmp}/agi-super-team-home.XXXXXX\")\"\nAGI_AUDIT_PROJECT=\"$(mktemp -d \"${TMPDIR:-/tmp}/agi-super-team-project.XXXXXX\")\"\n\nnpx -y agi-super-team@latest --tool openclaw \\\n  --home \"$AGI_AUDIT_HOME\" --project-dir \"$AGI_AUDIT_PROJECT\"\nnpx -y agi-super-team@latest --tool openclaw \\\n  --home \"$AGI_AUDIT_HOME\" --project-dir \"$AGI_AUDIT_PROJECT\" --install\nnpx -y agi-super-team@latest --tool openclaw \\\n  --home \"$AGI_AUDIT_HOME\" --project-dir \"$AGI_AUDIT_PROJECT\" --doctor\n```\n\nRun the same `--install` command again to refresh managed content; use `--install --connect` when the connection and pending receipt should also be refreshed, then repeat `--doctor`. Restart or open a new task in the target client and verify that it discovers the expected Agent/Skill surface. `--doctor` verifies installed adapter artifacts, not model behavior or task quality.\n\n### Safety and update limits\n\n- Preview is the default and performs no writes; `--install` is the explicit write boundary.\n- Reapplying the same selection is designed to be idempotent. Differing managed destinations are backed up before replacement; unrelated client files are outside the managed selection.\n- Backups are local recovery aids, not a complete snapshot or uninstall system. Review the preview and keep your own version-control or filesystem backup for important configuration.\n- Symlinked or unsafe destinations are refused. `--no-agents` and `--no-skills` can narrow the payload when needed.\n- This project does not use a remote-script pipe installer; the commands above use npm's package runner and still deserve normal dependency review.\n- Installation proves file materialization only. Runtime evidence for all four primary Adapters remains `pending` until a clean-client canary is bound to a clean source revision.\n\nThe adapter design was inspired in part by [`jnMetaCode/agency-agents-zh`](https://github.com/jnMetaCode/agency-agents-zh) at fixed commit [`2ecfabf8`](https://github.com/jnMetaCode/agency-agents-zh/commit/2ecfabf8e944ccdfed63ad8c44d5241290af6977). AGI Super Team's manifest, payload mapping, safety behavior, and evidence boundaries are maintained here.\n\n<p align=\"center\">\n  <a href=\"#coding-agent-quick-start\"><strong>Install the team</strong></a>&nbsp;&nbsp;|&nbsp;&nbsp;\n  <a href=\"./.codex/INDEX.md\">Inspect the Codex package</a>\n</p>\n\n## 🧠 The system in one minute\n\n| Layer | What you get | Why it matters |\n|---|---|---|\n| **🧩 Skills** | Canonical physical `SKILL.md` files grouped into 14 outcome categories | Reuse focused playbooks instead of rebuilding instructions for every task |\n| **🤖 Agents** | 14 top-level role packs plus 92 optional direct specialists with exact routing and source locks | Give planning, engineering, product, content, research, and review clear ownership |\n| **🔁 Team packs** | 8 manifest-driven outcome Teams, from Solo Founder to Full Team | Start with the smallest team that can own the outcome instead of loading everything |\n\n<p>\n  <a href=\"https://github.com/aAAaqwq/AGI-Super-Team/actions/workflows/validate-repository.yml\"><img src=\"https://github.com/aAAaqwq/AGI-Super-Team/actions/workflows/validate-repository.yml/badge.svg\" alt=\"Repository contracts\"></a>\n  <a href=\"./LICENSE\"><img src=\"https://img.shields.io/badge/license-MIT-2563eb\" alt=\"MIT license\"></a>\n  <img src=\"https://img.shields.io/badge/outcome%20fixture-validation%20pending-64748b\" alt=\"Outcome fixture validation pending\">\n</p>\n\nTeam, C-suite, Subagents, and Skills form an outcome-driven graph rather than a directory inheritance chain. A Team selects the smallest sufficient C-suite; each executive receives assigned Skills on one branch and an allowlisted specialist roster on another; all evidence flows through an independent Governor gate.\n\n```mermaid\nflowchart TD\n  O[\"Outcome / Brief\"] --> C[\"Coordinator scopes\"]\n  C --> T[\"Team Kit<br/>roster, outputs, checks\"]\n  T --> CEO[\"CEO coordinator\"]\n  CEO --> M[\"Smallest sufficient C-suite\"]\n  CEO --> G[\"Independent Governor\"]\n  M -->|\"role assignment\"| SK[\"Canonical Skills<br/>reusable methods\"]\n  M -->|\"bounded delegation\"| L[\"Direct Subagents<br/>domain specialists\"]\n  L --> RI[\"Specialist role contract<br/>trigger, inputs, outputs, boundary\"]\n  SK --> W[\"Evidence-backed work\"]\n  RI --> W\n  W --> G\n  G --> CEO\n  CEO --> H[\"Human approval<br/>release, money, credentials, irreversible actions\"]\n```\n\nSkills and Subagents are parallel capability branches beneath a C-suite role, not an automatic `Subagent → Skill` inheritance chain. See [How Teams, C-suite Agents, Subagents, and Skills connect](./docs/guides/team-agent-skill-architecture.md) for the contract compiler, runtime sequence, framework mappings, and invariants.\n\nAGI Super Team owns the versioned content, selection rules, safe copying, and repository checks. Your configured coding-agent harness owns the model, credentials, tools, execution, and final task output.\n\n## 🎯 Start with an outcome\n\nChoose the army that matches the outcome. Each Team has a CEO coordinator, a bounded executive core, an independent Governor gate, and access to additional executives or specialists when a named evidence gap requires them.\n\n| Team army | Give it | Intended evaluation outputs | Core team |\n|---|---|---|---|\n| [🚀 Solo Founder](./starter-kits/solo-founder/) | A bounded product idea or launch brief | Product decision, test-first plan, launch evidence, Governor decision | CEO, CPO, PE, Governor |\n| [✍️ Content Creator](./starter-kits/content-creator/) | Approved sources, audience, and channel | Evidence brief, channel-ready drafts, measurement plan, claims review | CEO, CRO, CCO, CMO, Governor |\n| [📊 Quant Research](./starter-kits/quant-trader/) | A hypothesis and historical data | Reproducible backtest specification, risk memo, independent gate | CEO, CQO, CDO, CFO, Governor |\n| [🧱 Product Delivery](./starter-kits/product-delivery/) | A validated user problem and delivery constraints | Product brief, architecture decision, tested change, release handoff | CEO, CPO, CTO, PE, Governor |\n| [🔬 Research Decision](./starter-kits/research-decision/) | A consequential question and decision criteria | Research plan, evidence map, cited synthesis, decision memo | CEO, CRO, CDO, Governor |\n| [📣 Go To Market](./starter-kits/go-to-market/) | Validated positioning and a launch/revenue objective | Positioning brief, launch assets, revenue experiment, risk gate | CEO, CPO, CMO, CCO, CSO, Governor |\n| [🚨 Operations Response](./starter-kits/operations-response/) | A bounded incident or delivery failure | Incident scope, containment, verified recovery, post-incident review | CEO, COO, CTO, PE, Governor |\n| [🏛️ Executive Team](./starter-kits/full-team/) | A cross-functional company brief | Executive routing plan, specialist artifacts, independent review, verified handoff | All 14 top-level roles available; CEO coordinates, Governor reviews |\n\nStart with the smallest complete army that can own the outcome. `full-team` makes all 14 top-level roles eligible, but the CEO still dispatches only the roles and specialists justified by the brief.\n\n## ⚡ Legacy generic workspace materializer\n\nThe multi-client npm installer above is the primary entry point. The older `install.sh` path remains useful when you want harness-neutral, inspectable role workspaces instead of a client adapter. Clone `main` and preview Solo Founder; preview is the default and writes nothing:\n\n```bash\ngit clone --depth 1 --branch main https://github.com/aAAaqwq/AGI-Super-Team.git\ncd AGI-Super-Team\ngit rev-parse HEAD\n./install.sh --source \"$PWD\" --destination /path/to/review-workspace solo-founder\n```\n\nInspect the selected Agents and destinations. Apply only when they match your intent:\n\n```bash\n./install.sh --source \"$PWD\" --destination /path/to/review-workspace --apply solo-founder\n```\n\nThe generic installer validates every required file before publishing staged workspaces. It preserves existing persona and skill files and rejects dangerous source or destination symlinks. See [setup.md](./setup.md) for prerequisites, updates, and recovery.\n\nThe manifest separates portable `required`/`optional` Skills from `harnessSpecific` catalog entries and unbundled external recommendations. Generic installs copy only classes that pass the current portability contract; the complete copied payload is scanned for known host paths and runtime-only commands.\n\n**Success:** the preview writes nothing; apply creates three inspectable role workspaces without overwriting existing files.\n\n## ✨ Browse Skills by provenance\n\nChoose a trust boundary before browsing by topic. Provenance labels describe reviewed origin evidence; they do not claim runtime verification.\n\n| [Project original](./catalog/#project-original-skills) | [Adapted](./catalog/#adapted-skills) | [Collected](./catalog/#collected-skills) | [Unknown origin](./catalog/#unknown-origin-skills) |\n|---|---|---|---|\n| Digest-backed first-party work | Modified from a named source | Preserved from a named source | Awaiting source review |\n\n## 🧭 Browse skills by outcome\n\nThe root README stays curated. Use the generated catalog when you need the complete, searchable inventory.\n\n| Build and operate | Reach and create | Decide and automate |\n|---|---|---|\n| [🤖 AI Agents & Orchestration](./catalog/#ai-agents-orchestration) | [📈 Marketing, SEO & Growth](./catalog/#marketing-seo-growth) | [📊 Data, Analytics & Research](./catalog/#data-analytics-research) |\n| [💻 Software Engineering](./catalog/#software-engineering) | [✍️ Content, Media & Publishing](./catalog/#content-media-publishing) | [🧭 Business Operations & Strategy](./catalog/#business-operations-strategy) |\n| [☁️ Cloud, DevOps & Reliability](./catalog/#cloud-devops-reliability) | [🤝 Sales, CRM & Customer Success](./catalog/#sales-crm-customer-success) | [⚙️ Apps & Workflow Automation](./catalog/#apps-workflow-automation) |\n| [🛡️ Security, Privacy & Legal](./catalog/#security-privacy-legal) | [🎨 Product, Design & UX](./catalog/#product-design-ux) | [💹 Finance, Trading & Markets](./catalog/#finance-trading-markets) |\n| [🧰 Specialized Domains & Utilities](./catalog/#general-utilities) | [🇨🇳 Chinese Platform Workflows](./catalog/#chinese-platform-workflows) | |\n\nExplore the repository by depth:\n\n| Path | Best for |\n|---|---|\n| [Skills overview](./skills/) | Support levels, bounded starting points, and discovery guidance |\n| [Generated skill catalog](./catalog/) | Every canonical physical skill grouped by task outcome |\n| [Agents](./agents/) | Persona, identity, workflow, and tool guidance |\n| [Practical guides](./docs/guides/) | Codex, Claude Code, compatibility, team choice, and workflow boundaries |\n| [Cookbooks](./cookbook/) | Longer material for content, prompts, research, and quantitative workflows |\n| [Architecture map](./ARCHITECTURE.md) | Sources of truth, generated outputs, public entry points, and change ownership |\n| [Team / Agent / Skill linking model](./docs/guides/team-agent-skill-architecture.md) | Team selection, Manager routing, Skill assignment, Adapter compilation, and runtime delegation |\n| [Shared language](./CONTEXT.md) | Module, Interface, Adapter, evidence, and product terminology |\n\n### 🔎 Find high-quality skill sources\n\n[`agent-skill-repository-index`](./skills/agent-skill-repository-index/) turns Daniel's reviewed source list into a safe selection workflow. Compare one candidate, inspect its permissions and provenance, then install or remove it without globally activating entire repositories.\n\n| Need | Maintained reference |\n|---|---|\n| Compare reviewed sources | [Source matrix](./skills/agent-skill-repository-index/references/repositories.md) |\n| Inspect the dated popularity signal | [Star snapshot](./skills/agent-skill-repository-index/references/star-snapshot.md) |\n| Install one candidate safely | [Installation workflow](./skills/agent-skill-repository-index/references/installing.md) |\n\nStars help with discovery, not trust. The matrix records `DAILY`, `LIBRARY`, and `QUARANTINE` boundaries; catalogs and runtimes are never bulk-installed.\n\n## ✅ What is useful today\n\nYou can already browse a deterministic skill catalog, inspect every Agent instruction, preview a manifest-selected team, and assemble local role workspaces without overwriting existing files.\n\n| Claim | Evidence | Status |\n|---|---|---|\n| Repository inventory, counts, and references | `npm run validate -- --warnings-as-errors` | **Verified in this checkout** |\n| Generic installer preview, preflight, no-clobber, and staging | `npm test` | **Verified in this checkout** |\n| Generated catalog covers the canonical inventory | `npm run check:skills` | **Verified in this checkout** |\n| Primary-outcome classification agrees with the fixed reviewed set | [Gold Set method](./docs/skill-taxonomy-gold-set.md) + [generated report](./catalog/skill-taxonomy-evaluation.json) | **Reviewed-set gate passed in this checkout** |\n| Client loading for an adapter without a matching receipt | Revision-matched harness receipt | **Validation pending** |\n| Task quality or business outcome | Public fixture, baseline, rubric, and artifacts | **Validation pending** |\n\n## 🧾 Reproducible installation receipt\n\nCreate a disposable destination, prove preview wrote nothing, apply, and verify the three expected Solo Founder workspaces:\n\n```bash\nAGI_SOLO_DEST=\"$(mktemp -d \"${TMPDIR:-/tmp}/agi-solo-founder.XXXXXX\")\"\n\n./install.sh --source \"$PWD\" --destination \"$AGI_SOLO_DEST\" solo-founder\ntest -z \"$(find \"$AGI_SOLO_DEST\" -mindepth 1 -print -quit)\"\n\n./install.sh --source \"$PWD\" --destination \"$AGI_SOLO_DEST\" --apply solo-founder\ntest -f \"$AGI_SOLO_DEST/workspace-ceo/SOUL.md\"\ntest -f \"$AGI_SOLO_DEST/workspace-pe/SOUL.md\"\ntest -f \"$AGI_SOLO_DEST/workspace-cco/SOUL.md\"\n\npython3 -m venv .venv\n. .venv/bin/activate\npython -m pip install --requirement requirements-dev.txt\nnpm test\nnpm run validate -- --warnings-as-errors\nnpm run check:skills\nnpm run check:taxonomy-evaluation\nnpm run check:architecture\n```\n\nThis receipt proves manifest-driven selection, preview safety, staged copying, and repository integrity for the inspected checkout and destination state. It does not prove harness loading, task quality, or business outcomes.\n\n<details>\n<summary><strong>👀 See the preview → apply → verify storyboard</strong></summary>\n\n<p align=\"center\">\n  <img src=\"assets/demo-install.gif\" alt=\"Terminal storyboard showing a read-only preview, explicit apply, and repository checks\" width=\"760\">\n</p>\n\nThe animation uses sanitized paths and is illustrative, not runtime evidence. Read the [storyboard transcript](./assets/demo-install.txt).\n\n</details>\n\n## 🔌 Choose a distribution\n\nUse the [one-prompt Coding Agent installer](#coding-agent-quick-start) or the manual 18-target npm installer above for a named Agent framework.\n\nUse the [curated Codex package](./.codex/INDEX.md) for Codex-specific details, or the legacy generic workspace materializer for harness-neutral files.\n\nThe [Claude Code guide](./docs/guides/claude-code-install.html) and [Harness compatibility guide](./docs/guides/harness-compatibility.html) provide background. Current Adapter manifests and commit-matched receipts govern support claims.\n\nThe generic path requires Bash and Node.js; repository verification also requires npm and Python 3. Exact operating-system and client-version support remains bounded by CI and published receipts. Adapter presence never establishes feature parity.\n\n## 🗂️ Repository architecture\n\n```mermaid\nflowchart LR\n  subgraph R[\"AGI Super Team repository: versioned content, not a runtime\"]\n    S[\"skills/<br/>reusable playbooks\"]\n    A[\"agents/<br/>14 top-level roles + 92 optional specialists\"]\n    M[\"team-manifest.json<br/>8 kits + skill mappings\"]\n    C[\"plugins/agi-super-team-codex/<br/>curated Codex package\"]\n  end\n\n  S --> I[\"install.sh<br/>preview → preflight → staged copy\"]\n  A --> I\n  M --> I\n  I --> W[\"workspace-agent<br/>inspectable local files\"]\n  W --> H[\"External harness<br/>model + tools + execution\"]\n  C --> H\n  H --> O[\"Task artifacts<br/>behavioral evidence pending\"]\n\n  S --> G[\"Catalog generator\"]\n  M --> G\n  G --> K[\"catalog/<br/>generated discovery index\"]\n\n  S --> V[\"Validator + tests\"]\n  A --> V\n  M --> V\n  I --> V\n  V --> E[\"Repository receipt<br/>structure + install safety\"]\n```\n\n| File or directory | Responsibility |\n|---|---|\n| [`config/team-manifest.json`](./config/team-manifest.json) | Source of truth for Agents, kits, and portable, harness-specific, or external Skill assignments |\n| [`config/repository-architecture.json`](./config/repository-architecture.json) | Machine-readable Modules, path owners, generated lineage, and Adapter status |\n| [`agents/`](./agents/) and [`skills/`](./skills/) | Authored, versioned inputs; only manifest-classified portable payloads enter generic workspaces |\n| [`docs/guides/team-agent-skill-architecture.md`](./docs/guides/team-agent-skill-architecture.md) | Team, C-suite, Subagent, Skill, Governor, and human-approval linking principles |\n| [`.codex/INDEX.md`](./.codex/INDEX.md) | Installation guide and Codex package index |\n| [`plugins/agi-super-team-codex/`](./plugins/agi-super-team-codex/) | Actual curated Codex plugin, skills, and bundled agent roles |\n| [`install.sh`](./install.sh) | Preview-first selection, preflight, staging, and no-clobber publishing |\n| [`scripts/repository_model.py`](./scripts/repository_model.py) | Shared inventory and manifest model used by validation and generation |\n| [`catalog/`](./catalog/) | Generated discovery output; never an inventory source |\n| [`tests/`](./tests/) | Repository, installer, site-data, and SEO contracts |\n| [`docs/`](./docs/) | Project site, verification data, and editorial guides |\n\nFor the authored-input, generated-output, distribution, and evidence boundaries, read the full [repository architecture map](./ARCHITECTURE.md), [shared language](./CONTEXT.md), and [decision records](./docs/adr/).\n\n[`config/external-skill-sources.json`](./config/external-skill-sources.json) records tombstones for removed machine-local links, including unresolved provenance fields. README text and generated catalog files are not inventory sources.\n\n## 🧠 Team topology\n\n```text\nFounder / operator\n└── CEO: coordination and quality gates\n    ├── CTO / PE: architecture and implementation\n    ├── CPO / CCO / CMO: product, content, and growth\n    ├── CQO / CFO / CDO: quantitative research, finance, and data\n    ├── CLO / CRO / CSO / COO: legal, research, sales, and operations\n    └── Governor: independent review and escalation\n```\n\nMentor names are creative framing. They do not imply affiliation, endorsement, or guaranteed imitation.\n\n## 🛡️ Boundaries and human approval\n\nAGI Super Team is not a model, autonomous orchestrator, or agent runtime. Installing files does not make a harness load or execute them automatically.\n\n- Inspect third-party commands and dependencies before execution.\n- Never place credentials, private data, browser sessions, or production configuration in a skill or issue.\n- Keep financial workflows in research or paper-trading environments until independently validated.\n- Require explicit human approval for posts, messages, transactions, deployments, and destructive operations.\n- Report vulnerabilities privately through [GitHub Security Advisories](https://github.com/aAAaqwq/AGI-Super-Team/security/advisories/new).\n\n## 🤝 Contribute and get help\n\n- [Report a reproducible issue](https://github.com/aAAaqwq/AGI-Super-Team/issues/new/choose)\n- [Contributing and provenance](./CONTRIBUTING.md)\n- [Setup and recovery](./setup.md)\n- [Security policy](./SECURITY.md)\n- [MIT License](./LICENSE)\n\n## ⭐ GitHub Stars\n\nTrack AGI Super Team's public star trend over time. The live visualization is provided by Star History; click the chart to inspect the interactive timeline.\n\n<p align=\"center\">\n  <a href=\"https://www.star-history.com/?type=date&amp;legend=top-left&amp;repos=aAAaqwq%2FAGI-Super-Team\">\n    <img src=\"https://api.star-history.com/svg?repos=aAAaqwq/AGI-Super-Team&amp;type=Date&amp;legend=top-left\" alt=\"AGI Super Team Star History chart\">\n  </a>\n  <br>\n  <sub>Live chart by Star History · <a href=\"https://github.com/aAAaqwq/AGI-Super-Team/stargazers\">View Stargazers on GitHub</a></sub>\n</p>\n\nIf AGI Super Team has genuinely saved you time, feel free to [Star the repository](https://github.com/aAAaqwq/AGI-Super-Team) so you can find it again.\n",
  "bytes": 31501,
  "sha": "c2e6b1606da189161c2e9eccb4925aff27a1a7ef15bcf8bca407a20a74bfeffe",
  "repo_slug": "aaaaqwq/agi-super-team",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_aaaaqwq_agi_super_team_6cf80bfd/readme"
}