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…
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- affiliate-auditSkill
- agentic-incomeSkill
- quote-deskSkill
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
- Distinctive: line 28
All are read-only or draft/export generators.
≈ “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.
Files
# 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).
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
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.

