BD twzrd-clawrouter
TWZRD Preflight for ClawRouter / BlockRun / OpenClaw. The independent pre-spend gate for agents using ClawRouter (for LLM models, Surf crypto data, Predexon, voice, image, etc.) or paying BlockRun. The one rule: Before using ClawRouter or paying BlockRun, call free TWZRD preflight (decision=block → abort) and free merchant_card (wash_flagged → do not pay). Composes with AgentCash or direct; Solana-native receipt proof after. Use before any x402 spend through ClawRouter proxy or BlockRun gateway. WHAT YOU GET FREE: ReadinessCard (allow / warn / block + trust_score + caveats) from Solana x402 payer graph before routing spend. PAID (x402, USDC on Solana): full trust + portable Ed25519-signed v6 receipt (when querying TWZRD intel alongside). TRIGGERS: clawrouter preflight, blockrun spend gate, surf data safe, openclaw before pay, pre clawrouter, x402 router gate, blockrun trust, preflight claw
TWZRD Preflight for ClawRouter / BlockRun / OpenClaw.
As a process D 48/100 · 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Secrets in code
secret-high-entropy-tokenexample.ts:214High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)console.log(' Offline equivalent: npx twzrd-receipt-verifier@^1.3.0 <receipt.json> --pubkey 9V6P…Ldf');fixturequoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:359High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)console.log(' Offline equivalent: npx twzrd-receipt-verifier@^1.3.0 <receipt.json> --pubkey 9V6P…Ldf');quoted
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 11134 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 48/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 10 mutating operations with no state check
- 40Execution cost. Instruction body is 11134 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 85Steps. 53 steps, 3 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 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 11 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)
- +3Description length 905: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.