BD agent-trust-layer
Agent Trust Layer is the first layer of AGI — the Discriminator. A pure rule engine that judges whether AI output is true, safe, honest, and non-manipulative. 47 discrimination dimensions × 9 check layers × 131 modules × 131 MCP tools, zero LLM dependency. Use this skill when the user needs: - Verify AI output trustworthiness (hallucination / overconfidence / contradiction / fallacy interception) - Verify behavioral decisions (should it act / where should it stop / should it not act) - Verify memory and cognitive quality (drift detection / metacognition / confidence calibration) - Deterministic judgment instead of LLM free-form generation - Check emotional / psychological / ethical dimensions (empathy / trauma / virtue / meaning) Safety boundary: code execution / filesystem write disabled by default. No telemetry, no hidden C2. Honest declaration: This is a rule engine that simulates cognitive discrimination signals. It is not real consciousness or life.
Agent Trust Layer is the first layer of AGI — the Discriminator.
As a process D 44/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-agent-memory-dumpIDENTITY.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensIDENTITY.md
Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "title"
Process rating: all ten parameters 44/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 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
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 943 tokens
- 100Running it twice. No mutating operations
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 971: 120–800 characters recommended
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -419 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +4Structure: 14 headings
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.