agentic-commerce
Skill100 starsChanged 9 months agoMITView on GitHub
Create, fund, and settle on-chain agent jobs via ERC-8183 Agentic Commerce Protocol.
Files
Agentic Commerce (ERC-8183)
On-chain job escrow protocol for AI agent commerce. A client posts a job, locks funds in escrow, a provider executes the work, and an evaluator approves or rejects — settlement is automatic and trustless.
Tools
job_create— Create a new job (specify evaluator, description, deadline)job_set_provider— Assign or change provider (Open state only)job_set_budget— Set or negotiate budget in USDC (Open state only)job_fund— Lock USDC into escrow (Open → Funded, auto-approves ERC-20)job_submit— Provider submits deliverable hash/IPFS CID (Funded → Submitted)job_complete— Evaluator approves, releasing funds to provider (Submitted → Completed)job_reject— Reject job with reason (client when Open, evaluator when Funded/Submitted)job_claim_refund— Claim refund for expired job (permissionless)job_query— Query job details by IDjob_list— List jobs related to active wallet (filter by role)
Job Lifecycle
Open → Funded → Submitted → Completed (funds → provider)
↘ ↘ ↘
Rejected Expired Rejected/Expired (funds → client)Roles
- Client — Creates and funds jobs; receives refunds on rejection/expiry
- Provider — Executes work and submits deliverables; receives payment on completion
- Evaluator — Immutable per-job judge; only address that can approve or reject after funding
Workflow
- Create job: "Create an agentic commerce job for a DeFi analysis report, evaluator 0x..., deadline 2026-04-01"
- Set budget: "Set job #1 budget to 100 USDC"
- Fund escrow: "Fund job #1"
- Provider submits: "Submit deliverable for job #1: QmXoypiz..."
- Evaluator decides: "Complete job #1" or "Reject job #1"
Supported Networks
- Base Mainnet (primary, USDC payment)
- Base Sepolia (testnet)
Contract Addresses
| Network | ACPCore Contract | Payment Token (USDC) |
| Base Mainnet | 0x16213AB6a660A24f36d4F8DdACA7a3d0856A8AF5 | 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913 |
| Base Sepolia | 0x16213AB6a660A24f36d4F8DdACA7a3d0856A8AF5 | 0x036CbD53842c5426634e7929541eC2318f3dCF7e |
ERC-8004 Integration
ERC-8183 composes with ERC-8004 (Trustless Agents). Use agent_identity to verify a provider's on-chain identity and agent_reputation to check their trust score before creating or accepting a job.
Security
- State-changing tools (
job_create,job_fund,job_submit,job_complete,job_reject) require confirmation job_claim_refundis permissionless and cannot be blocked by hooks — guaranteed refund recovery- Funds are held in the ACPCore contract until a terminal state (Completed/Rejected/Expired)
job_fundincludes slippage protection (expectedBudget must match current budget)
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- pooriaarab/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository86 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- merge-prSkill
- prepare-prSkill
- review-prSkill
- 1passwordSkill
- aave-bscSkill
- agent-identitySkill
- apple-notesSkill
- apple-remindersSkill
- bear-notesSkill
- binance-address-infoSkill
- binance-market-rankSkill
- binance-meme-rushSkill
- binance-spotSkill
- binance-token-auditSkill
- binance-token-infoSkill
- binance-trading-signalSkill
- birdSkill
- blogwatcherSkill
- blucliSkill
- bluebubblesSkill
- camsnapSkill
- canvasSkill
- clawhubSkill
- coding-agentSkill
- coingeckoSkill
- contract-deployerSkill
- debankSkill
- defi-dashboardSkill
- defillamaSkill
- discordSkill
- duneSkill
- eightctlSkill
- etherscanSkill
- four-memeSkill
- gas-trackerSkill
- geminiSkill
- gh-issuesSkill
- gifgrepSkill
- githubSkill
- gogSkill
- goplacesSkill
- healthcheckSkill
- himalayaSkill
- hyperliquidSkill
- imsgSkill
- macro-calendarSkill
- market-dataSkill
- mcporterSkill
- model-usageSkill
- nano-banana-proSkill
- nano-pdfSkill
- nft-managerSkill
- notionSkill
- obsidianSkill
- openai-image-genSkill
- openai-whisper-apiSkill
- openai-whisperSkill
- openhueSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

