affiliate-agent-skills
AGENTS.md2 starsChanged 5 months agoMITView on GitHub
This repo is part of the FrankX / Starlight / Arcanea agent estate. Trinity Income Portfolio: Sovereign Agentic Passive Income OS — Earn • Automate • Compound. - Stages: Earn (agenticincome), Automate (agenticpassiveincome), Compound (disruptivepassiveincome) - Shared engine now includes skill/agent registry + marketplace: versioned, discoverable, monetizable (100% keep or low-fee models), one-click deploy, template gallery. - Absorption of marketplace mechanics: registry in data/trinity-skill-registry.json + src/trinity-registry.ts (MCP-exposed actions, cross-agent registration). - Exportable skills: Every skill/command exportable as MCP tool, LangGraph…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository4 other files it gives its agents.
- llms.txtllms.txt
- affiliate-auditSkill
- affiliate-opsSkill
- agentic-incomeSkill
The file
We split this AGENTS.md into the rules it gives an agent
10 rules. About 1 is common, 7 are distinctive, and 2 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Default health command: npm run build && node -e "import('./dist/src/trinity-registry.js').then(m => console.log('Trinity Registry OK:', …
- Distinctive: line 25
Read this file before making changes.
- Distinctive: line 27
Keep edits scoped to the requested task.
- Distinctive: line 28
Prefer existing repo conventions over new abstractions.
- Distinctive: line 29
Run the health command before handoff when feasible.
- Common: line 30
Do not publish secrets, private memory, credentials, or internal-only strategy.
- Distinctive: line 31
Use repo-relative paths in committed files.
- Distinctive: line 37
Keep public/private memory boundaries explicit.
- Distinctive: line 55
When motion, scroll, generated media, GIF/video, or premium polish matters, route through the Motion Design Studio plugin/skills and verify …
- Very specific: line 59
All changes on main. Excellence review: build + registry load test + MCP action execution.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
Repository Instructions
This repo is part of the FrankX / Starlight / Arcanea agent estate.
Classification
- Repo: affiliate-agent-skills (Shared Engine)
- Class: Canonical Trinity Income Portfolio Registry + Marketplace
- Default health command: npm run build && node -e "import('./dist/src/trinity-registry.js').then(m => console.log('Trinity Registry OK:', m.loadTrinityRegistry().name))"
- Remote: https://github.com/frankxai/affiliate-agent-skills.git
- Local paths: use your own clone; committed files stay repo-relative.
Trinity Branding & Marketplace Absorption (2026-07-14)
Trinity Income Portfolio: Sovereign Agentic Passive Income OS — Earn • Automate • Compound.
- Stages: Earn (agenticincome), Automate (agenticpassiveincome), Compound (disruptivepassiveincome)
- Shared engine now includes skill/agent registry + marketplace: versioned, discoverable, monetizable (100% keep or low-fee models), one-click deploy, template gallery.
- Absorption of marketplace mechanics: registry in data/trinity-skill-registry.json + src/trinity-registry.ts (MCP-exposed actions, cross-agent registration).
- Exportable skills: Every skill/command exportable as MCP tool, LangGraph node, antigravity bundle, standalone package, or Hermes profile.
- Cross-agent registration: Hermes (profiles/MCP), Codex (.codex/skills/exec), Claude (CLAUDE.md/MCP), Grok (harness/prompts), Antigravity (awesome-skills/worktree).
- Public-trust: All entries verified via public-trust.test.mjs; honest marketing, verifiable execution proofs, no hype. Trust is the asset.
Agent Rules
- Read this file before making changes.
- Preserve existing user work and unrelated dirty files.
- Keep edits scoped to the requested task.
- Prefer existing repo conventions over new abstractions.
- Run the health command before handoff when feasible.
- Do not publish secrets, private memory, credentials, or internal-only strategy.
- Use repo-relative paths in committed files. Never commit absolute local paths, usernames, or machine-specific roots.
Class-Specific Guidance
- Preserve skill/plugin/MCP schemas and frontmatter.
- Validate skills, manifests, scripts, and generated registries after edits.
- Keep public/private memory boundaries explicit.
- Trinity actions MCP-exposed: trinity/diagnostics, trinity/stream/select, trinity/earn/audit, trinity/automate/deploy, trinity/compound/ledger, trinity/marketplace/list, trinity/marketplace/deploy, trinity/public-trust/verify.
- Marketplace: 100% keep default for free listings; low-fee (5-15%) on paid; one-click via deployScript + MCP.
Handoff
Summarize changed files, validation run, risks, and any follow-up needed.
Design Taste Kernel
For any site, app, landing page, dashboard, visual identity, brand, motion, media, social, or frontend task, apply the shared Design Taste Kernel before handoff:
<workspace>/DESIGN_TASTE.md<workspace>/WEB_EXPERIENCE_STANDARD.md<workspace>/MOTION_TASTE_RUBRIC.md<workspace>/MULTI_AGENT_DESIGN_COUNCIL.md<workspace>/VISUAL_QA_GATE.md
When motion, scroll, generated media, GIF/video, or premium polish matters, route through the Motion Design Studio plugin/skills and verify the result visually.
Production e2e Note
All changes on main. Excellence review: build + registry load test + MCP action execution. Push to main after verification. GitHub: https://github.com/frankxai/affiliate-agent-skills
Artifacts:
- data/trinity-skill-registry.json (registry + marketplace data)
- src/trinity-registry.ts (implementation + MCP exposure)
- Updated src/index.ts, README.md, AGENTS.md
- GitHub main: https://github.com/frankxai/affiliate-agent-skills/tree/main
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.

