Skip to content
Back to search

agent-creator

MarketplaceWorks with Claude CodeGitHub

Build a team of Claude Code agents for any project, with model routing per agent.

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/juan16pcxix--agent-creator/badge.svg)](/listings/juan16pcxix--agent-creator)

HTML

<a href="/listings/juan16pcxix--agent-creator"><img src="/api/listings/juan16pcxix--agent-creator/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** (recommended, gets updates):

/plugin marketplace add Juan16pcXIX/agent-creator
/plugin install agent-creator@agent-creator

**By hand**: copy `plugins/agent-creator/skills/agent-creator` into `~/.claude/skills/` (all projects) or `.claude/skills/` (one 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.

.claude-plugin/marketplace.json · Manifest · 14 lines
  1. {
  2. "name": "agent-creator",
  3. "description": "Build a team of Claude Code agents for any project, with model routing per agent.",
  4. "owner": {
  5. "name": "Juan16pcXIX"
  6. },
  7. "plugins": [
  8. {
  9. "name": "agent-creator",
  10. "source": "./plugins/agent-creator",
  11. "description": "Turns any project, brand, person or goal into a tree of Claude Code agents, each on the cheapest model that does its job well."
  12. }
  13. ]
  14. }
README.md · README · 113 lines
  1. # agent-creator
  2. **Give it a project. Get back a team of Claude Code agents, each on the cheapest model that can do its job well.**
  3. [Leer en español](README.es.md)
  4. agent-creator is a skill for [Claude Code](https://code.claude.com). Point it at a project folder, a conversation, or a short description ("a streetwear brand", "I make music", "our logistics paperwork"), and it:
  5. 1. **Reads the root**: what the project is, what work keeps repeating, and what you already have (your agents, skills and connectors such as Canva or Notion).
  6. 2. **Scans the field briefly**: how this kind of project is usually run and what is missing.
  7. 3. **Interviews you**: how expert the agents should be, your budget, where to install them, what language they work in.
  8. 4. **Draws a tree**: departments (branches) and single-purpose subagents (leaves), with a verifier wherever mistakes are expensive.
  9. 5. **Routes every agent to a model** with a 10-point rubric: Haiku for mechanical work, Sonnet for most production work, Opus for strategy and high-stakes calls.
  10. 6. **Lets you pick the team**, department by department: tick the agents you want, keep or upgrade the ones you already have, and add any agent it did not think of ("one that builds the carousels in Canva").
  11. 7. **Researches each department** at the depth you chose and writes it into knowledge files the agents read.
  12. 8. **Writes the agent files and an orchestrator skill** (`/your-project`) that routes requests to the right agent, and **validates the result** with a bundled script.
  13. ```
  14. norte (/norte)
  15. ├── marketing ── norte-marketing-lead [sonnet · medium]
  16. │ ├── strategist [opus · high] 2-4 week content and campaign plan
  17. │ ├── trend-scout [haiku · medium] this week's trends, with links
  18. │ ├── carousel-writer [sonnet · medium] one carousel from a brief
  19. │ └── fact-checker [sonnet · medium] checks claims, prices, dates
  20. └── finance (no lead: only two leaves)
  21. ├── bookkeeper [haiku · low] categorizes transaction exports
  22. └── cashflow-forecaster [opus · medium] 13-week forecast, risky weeks
  23. ```
  24. *A real output for a fictional clothing brand. All files are in [examples/clothing-brand](examples/clothing-brand/.claude).*
  25. ## Why
  26. Building a team of agents by hand takes hours, and most people end up with one of two bad teams: a few giant agents that do everything badly, or every agent on the most expensive model "to be safe". A Haiku call costs about a twentieth of a Sonnet call. If the mechanical half of your work runs on Haiku and only the strategy runs on Opus, the team does the same work for a fraction of the tokens.
  27. ## Install
  28. **As a plugin** (recommended, gets updates):
  29. ```
  30. /plugin marketplace add Juan16pcXIX/agent-creator
  31. /plugin install agent-creator@agent-creator
  32. ```
  33. **By hand**: copy `plugins/agent-creator/skills/agent-creator` into `~/.claude/skills/` (all projects) or `.claude/skills/` (one project).
  34. ## Use
  35. In Claude Code, inside your project:
  36. ```
  37. /agent-creator
  38. ```
  39. or just ask: "create a team of agents for this project", "split my brand into departments with agents". You can also describe a root that has no folder yet: "build me agents for my music career: I write, record vocals at home and release a single every 6 weeks."
  40. When it finishes you get `/your-project`, an orchestrator skill that knows the whole team, plus the agent files in `.claude/agents/`. Run `/agent-creator` again later to add, merge or remove agents: it reads the saved `team.json` and works as a diff.
  41. ## How models are chosen
  42. Each agent is scored 0 to 2 on five things: reasoning depth, ambiguity, cost of an error, horizon, and judgment. The total (0 to 10) maps to a model:
  43. | Score | Model | For |
  44. |---|---|---|
  45. | 0-4 | Haiku | Files, formatting, lookups, data entry, checklists |
  46. | 5-7 | Sonnet | Writing from a brief, coding, research, fact-checking |
  47. | 8-10 | Opus | Multi-week plans, strategy, money and high-stakes decisions |
  48. Then it adjusts: your budget moves everything up or down a tier, agents that run many times per request drop a tier, verifiers are never weaker than what they check, and anything an audience reads is at least Sonnet. Fable is used only if you choose "max quality". Full rubric: [model-routing.md](plugins/agent-creator/skills/agent-creator/references/model-routing.md).
  49. ## How the tree is cut
  50. - A **leaf** does one recurring job with one output and a checkable "done when". One-off tasks don't get agents.
  51. - Every department where mistakes cost money, reputation or truth gets a **verifier** that did not produce the work.
  52. - A **lead** agent exists only when a department has 3+ agents that need planning or sequencing. Otherwise the orchestrator calls them directly, which is cheaper.
  53. - 3 to 7 departments, 2 to 6 agents each.
  54. Details and archetypes (business, creator, musician, software, logistics, research, personal goals): [references/](plugins/agent-creator/skills/agent-creator/references).
  55. ## What's in the repo
  56. ```
  57. .claude-plugin/marketplace.json marketplace entry
  58. plugins/agent-creator/
  59. .claude-plugin/plugin.json
  60. skills/agent-creator/
  61. SKILL.md the 8 phases
  62. references/ decomposition, model routing, interview, research, archetypes
  63. templates/ leaf agent, lead agent, orchestrator skill, team map, team.json schema
  64. scripts/validate_team.py checks a generated team (stdlib Python)
  65. examples/
  66. clothing-brand/ a full generated team that passes validation
  67. musician/ a team map, in Spanish
  68. ```
  69. Check a generated team yourself:
  70. ```
  71. python plugins/agent-creator/skills/agent-creator/scripts/validate_team.py examples/clothing-brand/.claude --team norte
  72. ```
  73. ## Roadmap
  74. - [ ] More examples (software startup, logistics office, YouTube channel)
  75. - [ ] Cost estimate per typical request, measured on real runs
  76. - [ ] Evals: a fixed set of project descriptions and a rubric for the trees they should produce
  77. - [ ] Ready-made team packs per industry
  78. Ideas and pull requests are welcome. Open an issue with the kind of project you tried it on and the tree you got.
  79. ## License
  80. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

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