ace-context-engineering
Agentic Context Engineering: evolve context via bullets, deltas, and TF-IDF retrieval with validation scripts.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for ace-context-engineering, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
A Claude Code plugin implementing Agentic Context Engineering (ACE): it evolves working context through structured bullets and deltas, retrieves with TF-IDF, and ships schemas plus validation scripts. Runs production scripts and hooks that read and rewrite context/memory state, which is security-relevant as it controls what the agent remembers.
Key features and capabilities
- Bullet/delta context evolution
- TF-IDF retrieval with schemas
- Validation and production scripts
Use cases
- Self-improving agent context management
- Structured long-horizon memory for agents