Known Instructions Directory

Type: kb/types/generated-index.md

← Parent

• Agent memory system review (type-spec) - Review of an external agent memory or context-engineering system; source-tier marks code-grounded vs doc-grounded evidence
• Analyse an Agent Runtime (instruction) - Workshop baseline for analysing how an external agent runtime schedules work, assembles bounded calls, acts on external state, coordinates agents, and exposes control surfaces.
• Analyse an External System's Epistemic Architecture (instruction) - Determine whether and how an external memory subsystem or agentic system produces knowledge by tracing its epistemic objects, transformations, warrant, and authority routes.
• Analyse Memory and Context Persistence (instruction) - Workshop baseline for analysing persistent material, memory writes and maintenance, later consumption and read-back, context efficiency, activation evidence, and lifecycle controls in an agentic system.
• Prepare a Code-Grounded System Source (instruction) - Workshop baseline for safely preparing and pinning a local GitHub source checkout once for all lenses in an external agentic-system analysis.
• Review Instruction: pi_agent_rust vs zerostack
• Write Agent Memory System Review (instruction) - Write or update a local code-grounded agent memory system review from a GitHub repository reference, including checkout refresh, optional sub-agent drafting, semantic QA, and validation.