BD paylobster
Agent payment infrastructure on Base. Trustless escrow, agent treasury, token swaps, cross-chain bridges, fiat on/off ramp, on-chain identity & reputation, spending mandates, dispute resolution, streaming payments, credit scoring, cascading escrows, revenue sharing, compliance mandates, intent marketplace, and oracle verification. Use the hosted MCP server (paylobster.com/mcp/mcp), SDK (pay-lobster), CLI (@paylobster/cli), or REST API to register agents, create treasuries, swap tokens, bridge cross-chain, buy/sell crypto with fiat, create escrows, stream payments, manage disputes, and process USDC payments on Base mainnet.
As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 5
✓ No critical or high findings
Medium and low: 5
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:806High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Identity Registry | `0xA1…662` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:807High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Reputation | `0x02…b29` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:808High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Credit System | `0x4c…27a` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:809High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Escrow V3 | `0x70…89e` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:810High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| SpendingMandate | `0xd1…3f0` |
table
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7773 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 47/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 37 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 7773 tokens
- 100Steps. 36 steps
- 100Consistency. Name and required fields are in place
- low 13 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 630: enough signal without eating the budget
- +4Structure: 72 headings
- +3Step-by-step instructions: 36 items
- +4Has examples (48 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.