agentleFS
frankxaifrankxai/agentic-income-skills/llms.txt

agentic-income-skills

llms.txt5 starsChanged 45 days agoMITView on GitHub

Open MIT-licensed skills for building paid-work systems where a human principal owns the service, accounts, approvals, and money. Agents operate inside declared authority. No income is promised. This pack ships two skills. Both are plain markdown plus a bundled Node runtime where needed. Swap --skill agentic-income for --skill quote-desk to install only the second skill. Sixteen tools: list_income_models, get_income_model, search_partner_programs, get_partner_program, list_products, fit_check, get_playbook, describe_income_graph_schema, get_reference_income_graph, review_income_graph, draft_income_graph, draft_income_system_manifest, export_income_system_tasks, search_digital_economies, list_supply_costs, calculate_unit_margin. All are read-only or draft/export generators. None…

The file

We split this llms.txt into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All are read-only or draft/export generators.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 3,727 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# Agentic Income Skills

> Open MIT-licensed skills for building paid-work systems where a human principal owns the service, accounts, approvals, and money. Agents operate inside declared authority. No income is promised.

This pack ships two skills. Both are plain markdown plus a bundled Node runtime where needed.

## Install

```sh
npx skills add frankxai/agentic-income-skills --skill agentic-income
```

Swap `--skill agentic-income` for `--skill quote-desk` to install only the second skill.

## Skills

- `agentic-income`: discover -> validate -> build -> sell -> deliver -> prove. Turns a repeated professional workflow into a governed, sellable service with an Outcome Pack contract.
- `quote-desk`: permissioned local request -> editable draft -> reopen/recover -> inspectable export. Node 20+, no npm dependency, no connector, no account. MIT licence bundled inside the skill.

## MCP server

- Endpoint: https://www.agenticincome.ai/api/mcp
- Manifest: https://www.agenticincome.ai/.well-known/mcp.json
- Server `agentic-income` v1.0.0, transport `streamable-http`, capability `tools`.

Sixteen tools: `list_income_models`, `get_income_model`, `search_partner_programs`, `get_partner_program`, `list_products`, `fit_check`, `get_playbook`, `describe_income_graph_schema`, `get_reference_income_graph`, `review_income_graph`, `draft_income_graph`, `draft_income_system_manifest`, `export_income_system_tasks`, `search_digital_economies`, `list_supply_costs`, `calculate_unit_margin`.

All are read-only or draft/export generators. None writes to the server, charges money, places an order, or predicts revenue. Affiliate links are disclosed in the payload.

## Docs

- [SKILLPACK.md](SKILLPACK.md): pack contract, include/exclude, MCP pair
- [docs/MCP.md](docs/MCP.md): initialize, example calls, limits, affiliate disclosure
- [docs/EVIDENCE-CONTRACT.md](docs/EVIDENCE-CONTRACT.md): source tiers, claim fields, no-unsourced-number rule, corrections, draft approval

## Licence

MIT. See [LICENSE](LICENSE).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.