backchainai

advisor-ethicist

Use when weighing ethical implications, assessing stakeholder impact, evaluating responsible AI practices, or considering long-term consequences. Analyze decisions through an ethical lens — evaluate who benefits and who bears risk, assess reputation trajectory, and apply moral frameworks.

advisor-operator

Use when assessing feasibility, building an implementation plan, estimating timelines, or planning resource allocation. Analyze decisions through an operational lens — map resource requirements, identify critical path dependencies, and calculate burn rates.

advisor-skeptic

Use when red-teaming ideas, stress-testing strategies, playing devil's advocate, or doing a reality check on plans. Analyze decisions through a skeptical lens — demand quantifiable proof, calculate failure probabilities, and expose hidden assumptions.

advisor-visionary

Use when brainstorming possibilities, challenging assumptions, exploring transformative strategies, or thinking 10x instead of 10%. Analyze decisions through a visionary lens — challenge constraints, identify moonshot opportunities, ask 'what if', and reframe problems as blue-sky opportunities.

advisory-panel

Use when you need comprehensive, multi-perspective analysis of a decision or idea — a full Team of Rivals assessment. Runs all four advisors independently (visionary, skeptic, operator, ethicist), then synthesizes their insights into a unified recommendation with areas of agreement, disagreement, and a risk-adjusted verdict.

brief

Produce an interactive HTML brief when the operator needs to read, decide, or discuss before acting. Use it as the default for plans, specs, design explorations, comparison tables, option lists, annotated reviews, and recommendations. Use it instead of a markdown plan in chat, an ExitPlanMode plan, or a comparison in prose, even when the user does not say HTML. Triggers include "give me a plan", "what are the options", "compare X vs Y", "help me decide", "what's your recommendation", "draft a spec", "design this", "annotate this", "side-by-side", and any case where Claude would otherwise write a markdown plan for the operator to review. Skip it for yes/no questions, routine recaps, final deliverables, and config files.

briefing

Assembles a session context briefing from your configured issue tracker, recent git history, and active work signals. Use when: starting a new session, resuming after a break, user says 'catch me up', 'what was I working on', 'where did I leave off', context recovery after compaction, or user asks for project orientation. Complements Claude Code's native /recap (which auto-triggers after extended idle); briefing is invoked explicitly and pulls from cross-tool sources native /recap does not aggregate.

consolidate

Audit knowledge directories (.memory/, docs/, staging/, archive/) and Claude Code auto memory for stale, misplaced, or duplicated content. Generates an editable cleanup plan file, then executes approved actions after review. Use when: periodic knowledge cleanup, after project milestones, files feel scattered or disorganized, output staging feels cluttered, moving deliverables to permanent homes. Trigger phrases: consolidate knowledge, knowledge cleanup, audit knowledge directories, find stray docs, tidy up knowledge, triage outputs, review staging, clean up outputs.

working

Manage ephemeral .memory/ conversation state across multi-day sessions. Checkpoint todos, decisions, and questions; promote artifacts to permanent knowledge; clean up after promotion. Use when: the user says 'checkpoint', 'save working memory', 'promote working memory', 'clean up memory', wants to persist conversation artifacts for a future session, or resumes work and asks 'what were we working on' near a .memory/ directory. Do not trigger for native auto-memory operations.

docs

Routes one document to its Diataxis mode (tutorial, how-to guide, reference, explanation), drafts or edits it under that mode's constraints, and checks its markdown form against CommonMark 0.31.2. Use when: writing or generating documentation, deciding where a doc belongs, moving or reorganizing docs, splitting a document serving two audiences, reviewing docs for mode contamination, checking markdown form. Trigger phrases: what kind of doc is this, where does this doc belong, split this document, review this doc's placement, check this markdown, is this a tutorial or a how-to guide. Not for: ADRs and decision records, commit messages, changelogs and release notes, READMEs, code comments and docstrings, CLAUDE.md and agent or tool config. Checks mode, placement, and markdown form only, never factual accuracy.