Skip to content
Back to search

ai-org-team

MarketplaceWorks with Claude CodeGitHub

Build and run an AI organization in Claude Code.

Safety scan

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

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/rishabhberia--ai-org-team/badge.svg)](/listings/rishabhberia--ai-org-team)

HTML

<a href="/listings/rishabhberia--ai-org-team"><img src="/api/listings/rishabhberia--ai-org-team/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

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

**As a plugin:**

/plugin marketplace add <owner>/ai-org-team
/plugin install ai-org-team@ai-org-team

**Or as a plain skill:** copy `skills/ai-org-team/` into `~/.claude/skills/`.

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.

.claude-plugin/marketplace.json · Manifest · 14 lines
  1. {
  2. "name": "ai-org-team",
  3. "owner": {
  4. "name": "ai-org-team contributors"
  5. },
  6. "plugins": [
  7. {
  8. "name": "ai-org-team",
  9. "source": "./",
  10. "description": "Build and run an AI organization in Claude Code: departmental AIs under a Management AI, talking through monitored sub-sessions."
  11. }
  12. ],
  13. "description": "Build and run an AI organization in Claude Code."
  14. }
README.md · README · 92 lines
  1. # ai-org-team
  2. A Claude Code skill that builds and runs an **AI organization**: one AI per department, each in its
  3. own repo with its own charter, knowledge base and memory, coordinated by a **Management AI** that
  4. acts as chief of staff.
  5. ```
  6. Organization AI team
  7. │
  8. Management AI ← routing, orchestration, conflicts, the ledger
  9. │
  10. ┌──────────┬─────────┼──────────┬────────────┐
  11. Sales AI Legal AI Finance AI Operations AI …
  12. ```
  13. ## How it works
  14. - **Each department owns its domain.** It is the only source of truth for it, and the only AI
  15. accountable for its numbers.
  16. - **AIs talk through sub-sessions.** When one AI needs information from another, or wants it to do
  17. something, it starts a Claude Code session in that department's folder. It watches that
  18. session, talks to it while it works, and records the request in a shared ledger. No AI reads
  19. another department's knowledge base to answer from it.
  20. - **Every answer carries provenance:** source, as-of date, basis, confidence, and what is missing.
  21. Missing is never written as zero.
  22. - **No AI approves anything.** Sending, writing to live systems, merging, deploying and spending
  23. stop with a named human principal.
  24. - **Confidentiality walls** hold in every direction, including toward the Management AI. These
  25. cover pay, personal data, privileged legal material, client-confidential terms and credentials.
  26. - **Conflicts are recorded, never averaged.** When two departments disagree, both positions go to
  27. the principal.
  28. The reasoning behind each rule is in
  29. [`skills/ai-org-team/reference/architecture.md`](skills/ai-org-team/reference/architecture.md).
  30. ## Requirements
  31. - **The Claude desktop app (Code tab)**, or any Claude Code harness that can start a session in
  32. another folder and message a running session. The protocol is built on sub-sessions.
  33. - `git` and `python3` (standard library only).
  34. ## Install
  35. **As a plugin:**
  36. ```
  37. /plugin marketplace add <owner>/ai-org-team
  38. /plugin install ai-org-team@ai-org-team
  39. ```
  40. **Or as a plain skill:** copy `skills/ai-org-team/` into `~/.claude/skills/`.
  41. ## Use
  42. Ask Claude something like:
  43. > Set up an AI team for my company with Sales, Legal, Finance and Operations.
  44. **You design the structure.** The skill asks what your organization does, proposes departments
  45. from a menu of common ones, and lets you add, drop, rename, merge, or split a department into
  46. several AIs (for example two Sales AIs, one per business line). It shows you the org chart
  47. (`scaffold.py --preview`) and changes it until you approve. Then it interviews you on each AI's
  48. scope, restrictions, systems and the confidentiality walls, and generates:
  49. | Repo | Contents |
  50. |---|---|
  51. | Management AI | `CLAUDE.md` charter; `knowledge/registry/` (department directory, capability matrix, systems map); `knowledge/protocol/` (interop protocol, data-sharing walls, escalation and authority); `knowledge/group/` (decision register, business context); `exchange/REGISTER.md` (the ledger); `logs/` |
  52. | Each department | `CLAUDE.md` charter with the team section; `knowledge/interop/ai-team.md` (team map and how to ask); `knowledge/00-INDEX.md`; `open-items.md`; `logs/` |
  53. Each AI's name, folder and knowledge-base folder are yours to choose. Existing projects can join
  54. as departments. Their `CLAUDE.md` is never overwritten. The skill
  55. writes a charter section for you to merge.
  56. It also covers adding, changing and retiring a department, changing the protocol across all
  57. departments, and a read-only health check (`scripts/check.py`).
  58. ### Optional modules
  59. - **Principal's office**: the Management AI also supports the principal directly. It handles
  60. briefs, follow-ups and drafts (never sent), and keeps personal matters walled off.
  61. - **PIAF** (Process Implementation & Assurance Framework): every new process or feature states its
  62. Promise, Proof and Protection, and production releases are checked against assurance gates.
  63. ## Try the scaffold without Claude
  64. ```bash
  65. python3 skills/ai-org-team/scripts/scaffold.py skills/ai-org-team/examples/example-config.json --preview
  66. ```
  67. ## License
  68. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

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