typescript-sdk

Use when performing root-cause analysis on a Prefactor agent run — bad output, surprising behavior, high cost, incomplete work, downvotes, or anything worth investigating. Run in the agent's own codebase. User provides agent instance ID (and agent ID if needed).

Use when choosing which Prefactor SDK skill to load for agent instrumentation or for building a custom provider integration on top of @prefactor/core.

Use when writing or fixing span summary templates (display templates) on Prefactor span type schemas, when spans show raw JSON or blank summaries in the Prefactor UI, or when you want one-line Liquid summaries of agent, llm, tool, and custom spans.

Review proposed or newly written tests for relevance, behavioral value, and maintainability. Use when Codex writes tests, reviews test diffs, receives feedback that tests are unnecessary, or needs to detect "bullshit tests": tests outside scope, tests written only for coverage, tests for impossible/unrealistic cases, tests coupled to implementation details, stale tests that should be removed, or tests adjacent to but not required by the feature.

Codebase health scanner and technical debt tracker. Use when the user asks about code quality, technical debt, dead code, large files, god classes, duplicate functions, code smells, naming issues, import cycles, or coupling problems. Also use when asked for a health score, what to fix next, or to create a cleanup plan. Supports 29 languages.

Codebase health scanner and technical debt tracker. Use when the user asks about code quality, technical debt, dead code, large files, god classes, duplicate functions, code smells, naming issues, import cycles, or coupling problems. Also use when asked for a health score, what to fix next, or to create a cleanup plan. Supports 29 languages.

Use when an agent is already instrumented with Prefactor and you need to populate data_risk fields on its span types to enable compliance tracking and data governance.

Use when an existing agent needs Prefactor resources created via the Prefactor CLI before SDK instrumentation is added.

Use when building a custom provider integration on top of @prefactor/core so your app can instrument agent, llm, and tool workflows without relying on a prebuilt adapter package.

Use when an existing agent already works without Prefactor and you need to add tracing for runs, llm calls, tool calls, and failures with minimal behavior changes.