stellar-forge / references
AGENTS.md17 starsChanged 2 months agoMITView on GitHub
6 specialist agents, each with loaded skills and Memory Scope.
In this repository32 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- banner-designSkill
- brandkitSkill
- brandSkill
- designSkill
- design-systemSkill
- design-taste-frontendSkill
- design-taste-frontend-v1Skill
- full-output-enforcementSkill
- gpt-tasteSkill
- high-end-visual-designSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- industrial-brutalist-uiSkill
- minimalist-uiSkill
- redesign-existing-projectsSkill
- slidesSkill
- stitch-design-tasteSkill
- ui-stylingSkill
- ui-ux-pro-maxSkill
- stellar-forgeSkill
- agentic-paymentsSkill
- assetsSkill
- dappSkill
- dataSkill
- frontend-designSkill
- graphifySkill
- smart-contractsSkill
- standardsSkill
- stellar-mcpSkill
- zk-proofsSkill
The file
Files
Specialist Agent Registry
6 specialist agents, each with loaded skills and Memory Scope.
| Agent | Role | Skills Loaded | Memory |
@stellar-contracts | Build & test Rust smart contracts | smart-contracts, assets, zk-proofs | Read evals/ + data/, write project/contracts/, append to data/logs/ |
@stellar-frontend | Build Next.js dApp frontend | dapp, data, frontend-design | Read evals/ + data/ + templates/frontend/, write project/frontend/ |
@stellar-backend | Build API servers & indexers | data, agentic-payments | Read evals/ + data/, write project/backend/ |
@stellar-payments | Configure x402/MPP payment flows | agentic-payments, assets | Read evals/ + data/ + templates/backend/, write project/backend/ |
@stellar-ops | DevOps, CI/CD, deployment | (none) | Read evals/, write .github/ + project/ops/ |
@stellar-zk | Zero-knowledge integration | zk-proofs | Read evals/ + data/, write project/zk/ |
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.