thoughtbox

A-Mem thought evolution — check which prior thoughts should be updated when a significant new insight arrives. Spawns a lightweight subagent to classify prior thoughts as UPDATE or NO_UPDATE, then applies revisions. Use during long reasoning sessions when you reach a synthesis, make a decision, or discover something that changes earlier assumptions. Triggers on "this changes what I thought earlier", "update prior reasoning", "evolve thoughts", or automatically on conclusion/synthesis thoughts in sessions >10 thoughts.

Cross-session knowledge retrieval from the Thoughtbox knowledge graph. Searches entities, traverses relations, retrieves observations, and synthesizes findings from past sessions. Use when you need to recall prior decisions, check what's already known about a topic, find related insights, or build on past work. Triggers on "what do we know about", "have we seen this before", "recall", "prior decisions about", "knowledge graph", or when starting work that might have prior context.

Capture significant learnings from the current work session. Structures insights for future sessions and updates agent memory.

Write or improve prompts for Codex using Anthropic's official best practices. Creates system prompts, agent prompts, tool descriptions, and MCP resource templates. Pass an existing prompt to improve it, or describe what you need to create one from scratch.

Generate architecture diagrams for a codebase subsystem or module. Explores source files and produces Mermaid diagrams in docs/.

Extract reusable principles and decision frameworks from accumulated experience. Use after significant work sessions, project milestones, or when you notice recurring patterns worth codifying.

Format a structured escalation to the human decision-maker (Chief Agentic). Use when hitting an escalation threshold.

Run parallel experiments across git worktrees. Define competing approaches to the same problem, dispatch sub-agents to implement each in isolation, then compare results. Use when you have 2-5 alternatives and want to test all of them before committing to one.

Implement a specification using a TDD-oriented workflow. Extracts requirements, generates tests first, then implements to pass the tests. Includes spiral detection and acceptance gates.

Execute a research task using compositional workflow planning. Characterizes the task, selects an approach from a library of research strategies, executes it, and self-evaluates output quality.

Generate a structured session summary for cross-session continuity. Captures key decisions, hypotheses, partial work, and knowledge references. Output is written to .Codex/session-handoff.json for the next session to load automatically.

Fuse insights from multiple knowledge sources (code, docs, memory, research, web) into coherent understanding. Use when you have scattered information that needs integration.

Run a taste evaluation on a research proposal or technical direction. Determines whether to proceed, simplify, defer, or kill before committing research effort.

Trigger when debugging something unexpected — a test failure, surprising behavior, production incident, or any situation where initial attempts aren't working. Prevents the common agent failure mode of trying random things when stuck. Use when "the first fix didn't work", "this is behaving unexpectedly", "I'm stuck", "why is this happening", or after 2+ failed attempts to fix something.

Structure decisions with parallel hypothesis exploration and knowledge graph persistence. Triggers on: "decide", "choose between", "which approach", "compare options", "evaluate alternatives", "tradeoff analysis".

A-Mem thought evolution — check which prior thoughts should be updated when a significant new insight arrives. Spawns a lightweight subagent to classify prior thoughts as UPDATE or NO_UPDATE, then applies revisions. Use during long reasoning sessions when you reach a synthesis, make a decision, or discover something that changes earlier assumptions. Triggers on "this changes what I thought earlier", "update prior reasoning", "evolve thoughts", or automatically on conclusion/synthesis thoughts in sessions >10 thoughts.

Cross-session knowledge retrieval from the Thoughtbox knowledge graph. Searches entities, traverses relations, retrieves observations, and synthesizes findings from past sessions. Use when you need to recall prior decisions, check what's already known about a topic, find related insights, or build on past work. Triggers on "what do we know about", "have we seen this before", "recall", "prior decisions about", "knowledge graph", or when starting work that might have prior context.

Gateway orientation for agents using Thoughtbox MCP for the first time. Use this skill when you connect to a Thoughtbox MCP server and need to understand what's available, how to structure reasoning sessions, or how to use the tb SDK. Also use when you're unsure which Thoughtbox operation to use for a task, or when you want to check what modules and patterns are available. Triggers on first Thoughtbox interaction, "how do I use Thoughtbox", "what can Thoughtbox do", or any confusion about Thoughtbox operations.

Friction-gated refactoring using the Theseus protocol. Prevents scope creep and refactoring fugue state by enforcing file scope boundaries, visa-based expansion, checkpoint audits, and a brittleness counter. Use when refactoring code, restructuring modules, renaming across files, or any task where "structure changes but behavior must stay the same". Triggers on "refactor", "restructure", "rename across", "extract module", "move code", or when a change touches 3+ files without adding features.

Analyze completed Thoughtbox sessions to extract patterns, anti-patterns, and learnings for the knowledge graph. This is the learning loop that makes Thoughtbox improve over time. Use after completing a reasoning session, when reviewing past sessions for insights, or when you want to assess reasoning quality. Triggers on "review session", "what did I learn", "extract insights", "analyze reasoning", "session retrospective", or proactively after any significant session completes.

Spawn an Agent Team with a background Thoughtbox analyst teammate. The analyst monitors your reasoning sessions for evolution candidates, contradictions, and generates periodic digests. Use this at the start of any deep Thoughtbox reasoning session, when you're about to record many thoughts and want background analysis. Triggers on "start thoughtbox team", "I want a session analyst", "monitor my reasoning", or at the start of any session where you plan to use Thoughtbox extensively.

Evaluate whether an idea is worth implementing by asking structured questions about outcomes, alignment, and opportunity cost. Stage 1 of the development workflow.

Finalize the workflow by reflecting on the process, moving ADRs, closing issues, and preparing for merge. Stage 8 of the development workflow.

Iterate on implementation fixes surfaced by review until all claims are verified. Stage 6 of the development workflow.

Orchestrate the full development lifecycle from ideation through merge. Sequences 8 stages with gates, dispatches to stage skills, and maintains workflow state.

Execute an implementation by dispatching multiple sub-agents to parallel Git worktrees. Each builds the entire feature independently, and the best implementation is selected and merged.

Capture learnings from the workflow into reusable documentation. Stage 7 of the development workflow.

Transform spec (with frontmatter claims) into an implementation plan with task decomposition and sub-agent assignment. Stage 3 of the development workflow.

Verify implementation claims by dispatching review agents. Stage 5 of the development workflow.

Execute the implementation plan by dispatching sub-agents for each task. Stage 4 of the development workflow.

Capture significant learnings from the current work session. Structures insights for future sessions and updates agent memory.

Write or improve prompts for Claude using Anthropic's official best practices. Creates system prompts, agent prompts, tool descriptions, and MCP resource templates. Pass an existing prompt to improve it, or describe what you need to create one from scratch.

Extract reusable principles and decision frameworks from accumulated experience. Use after significant work sessions, project milestones, or when you notice recurring patterns worth codifying.

Generate a structured session summary for cross-session continuity. Captures key decisions, hypotheses, partial work, and knowledge references. Output is written to .claude/session-handoff.json for the next session to load automatically.

Fuse insights from multiple knowledge sources (code, docs, memory, research, web) into coherent understanding. Use when you have scattered information that needs integration.

Spawn an Agent Team with a background Thoughtbox analyst teammate. The analyst monitors your reasoning sessions for evolution candidates, contradictions, and generates periodic digests. Use this at the start of any deep Thoughtbox reasoning session, when you're about to record many thoughts and want background analysis. Triggers on "start thoughtbox team", "I want a session analyst", "monitor my reasoning", or at the start of any session where you plan to use Thoughtbox extensively.

Run an Agent-Native Architecture Audit using Thoughtbox Hub for multi-agent coordination. Spawns 3 auditor agents and 1 synthesizer that collaborate through structured channels, cross-reference findings, and build consensus on scores.

Orchestrate a multi-agent collaboration demo on the Thoughtbox Hub. Spawns MANAGER, ARCHITECT, and DEBUGGER agents that coordinate through shared workspaces, problems, proposals, and channels.

Run an Agent-Native Architecture Audit using Thoughtbox Hub for multi-agent coordination. Spawns 3 auditor agents and 1 synthesizer that collaborate through structured channels, cross-reference findings, and build consensus on scores.

Orchestrate a multi-agent collaboration demo on the Thoughtbox Hub. Spawns MANAGER, ARCHITECT, and DEBUGGER agents that coordinate through shared workspaces, problems, proposals, and channels.