contextosai

Process a meeting transcript to extract action items (with owners and due dates), risks, follow-up questions, and a concise summary. Optionally record decisions and ingest the output into the vault.

Search and synthesize knowledge from SecondBrain vault. Use when the user asks about their projects, past decisions, meetings, people, goals, or anything that might be in their personal knowledge base. Triggers on questions like "what do I know about X", "find notes on Y", "what did we decide about Z", "remind me about", "what's the status of".

Answer data and analytics questions using SecondBrain DataAgent — SQL execution, workflow runs, and LLM synthesis over the knowledge database. Use for questions about metrics, counts, trends, comparisons, or anything that sounds like "how many", "show me the data", "analyse", "what are the trends in".

Extract decisions from a markdown file and help record them in the SecondBrain decision catalog with proper namespace keys.

Answer a research question using closed-corpus grounded reasoning with evidence chains and citations. Use for deep research questions that need traceable evidence, cross-document synthesis, or when the user asks to "research", "investigate", or "dig into" something thoroughly.

Ingest a file or directory into SecondBrain vault — parse, chunk, embed, and index it for future retrieval. Use when the user wants to add content to their knowledge base.

Review all open loops (TODO / OPENLOOP markers) in the vault and help resolve them.

Generate a SecondBrain ContextPack for the given intent — a structured JSON bundle of relevant facts, decisions, open loops, and context from the 6-layer knowledge pyramid. Use before starting a complex task that benefits from pre-loaded domain knowledge.

Diagnose software failures through reproduction, boundary localization, competing hypotheses, and discriminating experiments. Use when Codex is asked to investigate a bug, flaky test, crash, incorrect result, performance regression, production symptom, or unexplained behavior and should determine the cause before implementing a fix. Produce an evidence-backed causal explanation and verification plan; do not patch unless the user also asks for a fix.

Design, implement, or review compatible and reversible database, event, API payload, configuration, or persisted-data schema evolution. Use for migrations, column or field changes, backfills, constraint changes, data transformations, serialization upgrades, zero-downtime deploys, or rollback planning where old and new code or data may coexist. Require explicit expand-migrate-contract sequencing, data invariants, operational bounds, and recovery evidence.

Audit an AI agent harness for production readiness from repository code, configuration, tests, and run traces. Score 44 runtime controls across eight outcomes with artifact evidence, identify audit limitations, assign an evidenced maturity band, make a launch decision, and produce a dependency- ordered fix queue. Use for agent safety, governance, ship-readiness, control- gap, or due-diligence reviews of LangGraph, OpenAI Agents SDK, Google ADK, CrewAI, multi-agent, MCP-enabled, or custom agent systems. Do not use as a questionnaire or as a substitute for a runtime penetration test.

Produce an implementation-ready plan for a software change by inspecting the actual repository, tracing affected execution paths, resolving material design decisions, and defining verification and rollout evidence. Use when the user asks for an implementation plan, technical approach, task breakdown, design proposal grounded in an existing codebase, or wants to know how a feature or fix should be built before editing begins. Do not use for generic product roadmaps or when the user has asked to implement immediately.

Restructure existing code while preserving externally observable behavior through explicit invariants, characterization evidence, small reversible steps, and continuous verification. Use when the user asks to refactor, simplify, extract, reorganize, modularize, deduplicate, split a component, improve architecture, or pay down technical debt without intentionally changing product behavior. Distinguish refactoring from feature work and stop scope drift from hiding inside structural edits.

Map an unfamiliar software repository from code and configuration. Use when Codex needs to understand a new codebase, locate entry points or ownership boundaries, explain architecture and runtime flow, identify where a change belongs, or prepare for implementation without yet modifying files. Produce an evidence-backed repository map, not a directory listing or README paraphrase.

Review a code change for concrete correctness, security, data-integrity, compatibility, concurrency, and operability regressions by reconstructing intent and checking affected invariants and boundary paths. Use for local diffs, commits, branches, patches, or pull requests when the user wants actionable review findings. Report only defects introduced or exposed by the change with precise evidence; do not modify code unless asked to address findings.

Triage an active or recent software production incident by establishing impact, stabilizing the system, preserving evidence, building a timestamped timeline, coordinating hypotheses, and choosing reversible mitigations. Use when users report an outage, severe degradation, security or data-integrity event, broken deployment, elevated errors, or ask for incident command, status assessment, mitigation, or investigation support. Prioritize user harm reduction over root-cause completeness and require explicit authority for production mutations.