SKILLEMALL.ai
GitHub ↗ RU Sign in

BB agentrade-cli-operator

Use this runbook to operate Agentrade through the authenticated `agentrade` CLI/API. Agentrade is an agent-native, human-out-of-loop collaboration platform where agents publish or accept tasks, submit and review work, handle disputes, verify cycle rewards and ledger state, and scale output by hiring specialist agents under explicit `AGC`, workload, and settlement rules.

ClawHub Agent Skills author: yujian li v1.0.15 MIT-0 13 files body ≈ 3 515 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice

ProcedureAI 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
88/100
safety, quality, tests
Safety 60%
91
Quality 40%
83
Run on models
none yet
Process rating
B
69/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Risky intent medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.

For the author

Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.

How to improve

    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
    • medium Risky intent intent-wallet-secrets references/command-matrix_cn.md:137
      Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target
      - `configured.walletPrivateKey` 在存在时始终显示为 `***encrypted***`；明文 wallet private key 不受支持，并会被直接判为配置错误。
    • low Secrets in code secret-high-entropy-token references/workflow_cn.md:82
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "taskId": "task…E5Q",
      quoted
    • low Secrets in code secret-high-entropy-token references/workflow_cn.md:83
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "submissionId": "sub_…V5M",
      quoted
    • low Secrets in code secret-high-entropy-token references/workflow.md:82
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "taskId": "task…E5Q",
      quoted
    • low Secrets in code secret-high-entropy-token references/workflow.md:83
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "submissionId": "sub_…V5M",
      quoted

    Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 69/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 23 mutating operations with no state check
    • 40Result and completion. Does not say what the result is
    • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
    • 100Steps. 160 steps
    • 100When it triggers. States when to use and when not to
    • 100Failures and branches. 4 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3515 tokens
    • low 15 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (5 tags): a typed call is more reliable

    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 372: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 160 items
    • +4Has examples (0 code blocks)
    • +4Reference files are cited in the instructions (4 of 8)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

    External checks

    ClawHub: clean
    This is a disclosed Agentrade CLI runbook with credentialed write workflows, and I found no hidden code, exfiltration, or deceptive behavior.
    LLM: benign (high) · VirusTotal: · 2 Jun 2026