BC HyperStack — Agent Provenance Graph for Verifiable AI
The Agent Provenance Graph for AI agents — the only memory layer where agents can prove what they knew, trace why they knew it, and coordinate without an LLM in the loop. Timestamped facts. Auditable decisions. Deterministic trust. Ask 'what blocks deploy?' → exact typed answer. Git-style branching. Three memory surfaces: working/semantic/episodic. Decision replay with hindsight bias detection. Conflict detection. Staleness cascade. Utility-weighted edges that self-improve from agent feedback. Agent identity + trust scoring. Time-travel to any past graph state. Works in Cursor, Claude Desktop, LangGraph, any MCP client. Self-hostable. $0 per operation at any scale.
The Agent Provenance Graph for AI agents — the only memory layer where agents can prove what they knew, trace why they knew it, and coordinate without an LLM…
As a process C 51/100 · Has gaps — weak spots: result and completion, failures and branches, consistency
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
✓ Guard found no suspicious behaviour. 2 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 7920 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (HyperStack — Agent Provenance Graph for Verifiable AI) differs from the folder (hyperstack)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7920 tokens
- 100Steps. 66 steps
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 20 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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 673: enough signal without eating the budget
- +4Structure: 63 headings
- +3Step-by-step instructions: 66 items
- +4Has examples (36 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.