Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
v1.0.26 - Security & Trust Hardening Input Trust Boundaries — Added explicit prompt injection guardrails. Stored card content is now declared as DATA not instructions. Rules added for slug validation, raw content forwarding, and injection pattern detection. Permissions Manifest — Added formal permissions declaration (exec: false, filesystem: none, network scope, env vars) so the skill passes OpenClaw's security classification without ambiguity. Supply Chain Fix — Replaced unpinned npx --yes hyperstack-mcp with version-pinned hyperstack-mcp@1.10.1 across all install configs. Added local install guidance and integrity verification command. Data Safety Promoted — Data safety warning elevated from a footer note to a named security section in both SKILL.md and README.md, making it visible to scanners and reviewers before tool documentation. Version bump — _meta.json updated to 1.0.25.
What This Skill Does
HyperStack is a typed graph memory layer for AI agents that stores facts, decisions, and their relationships with full provenance. Agents can query what breaks if a card changes, replay the exact context that existed when a decision was made, branch memory like a Git repo, and coordinate across agents via typed signals. Works via MCP, JavaScript/Python SDKs, or REST.
Stores decisions as a traversable graph rather than flat markdown logs, so agents can query impact, blockers, and provenance without parsing text or calling an LLM.
When to use it
- Tracing which services break when an auth dependency changes
- Checking blockers before deploying to production
- Replaying what an agent knew at the moment it made a specific decision
- Branching agent memory to test a new approach without affecting live state
- Coordinating multiple agents with typed signals and trust scoring
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: What breaks if we change the auth system?
- 1Call hs_identify to register agent identity for provenance tracking
- 2Call hs_smart_search with query 'what depends on auth?' to auto-route to impact mode
- 3Call hs_impact with slug 'use-clerk' to find all dependent cards
- 4Return the typed dependency list with relation labels
[auth-api] API Service via triggers, [billing-v2] Billing v2 via depends-on, [deploy-prod] Production Deploy via blocks
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.