SKILLEMALL.ai
GitHub ↗ RU Sign in

BC clawshake

Trustless USDC escrow for autonomous agent commerce on Base L2. Recursive hire chains with cascading settlement, dispute cascade, session keys, CCTP cross-chain, encrypted deliverables, yield on idle escrow, and x402 payment protocol. 7 deployed contracts, 127 tests (57 security-specific).

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 5 685 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Trustless USDC escrow for autonomous agent commerce on Base L2.

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
95
Quality 40%
74
Run on models
none yet
Process rating
C
54/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • 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-token SKILL.md:303
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **ShakeEscrow** | `0xa3…C61` | Core escrow — recursive hire chains, dispute cascade, cascading settlement |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:304
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **AgentRegistry** | `0xdF…33E` | SBT passports, skill index, reputation tracking |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:305
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **FeeOracle** | `0xfB…FEE` | Dynamic depth-based fees (base + depth premium) |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:306
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **AgentDelegate** | `0xe4…fDc` | Session keys — spend-limited, time-bounded delegation |
    table
  • low Secrets in code secret-high-entropy-token SKILL.md:307
    High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
    | **CrossChainShake** | `0x27…f68` | CCTP v2 cross-chain shake initiation/fulfillment |
    table

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5685 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 54/100

  • 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. 12 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 70Execution cost. Instruction body is 5685 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 40 steps
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 16 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
  • +1No license
  • +2Single-language instructions
  • +3Description length 290: enough signal without eating the budget
  • +4Structure: 43 headings
  • +3Step-by-step instructions: 40 items
  • +4Has examples (32 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.