A read-only investigation mode for finding root causes, semantic drift, or incomplete capabilities before making changes. It prevents project files from being edited during diagnosis.
Use when the user wants one simple entry to initialize, update, repair, migrate, or resume the CoTend development framework, or asks whether a project can continue under it. Delegates once to the currently installed Project Init, propagates its canonical result, and returns one outer handback without becoming a second…
Use when a project may benefit from a stronger model or changes carrier, provider, actual model, material configuration, or role. Separate identity and role; classify advisor, trial, confirmed-primary, and rollback changes; prepare evidence-backed advisor or takeover packets; make non-authorizing Full/Adaptive…
Initialize, update, repair, migrate, or resume under CoTend, including named upstream Dual handoff/adoption/install or an external platform-adapter sync. Resolves impact before broad reads, loads triggered owners, preserves protected boundaries, validates real governance writes, and returns one handback.
Literal-gated CoTend control Skill. Eligible only when the current input contains $cotend-session-handoff. After that gate, load one direct same-Primary handoff workflow; identity or role changes route to cotend-model-upgrade.
Inventory, reconcile, collect, verify, index, find, evaluate, adopt, refresh, or retire reusable development capabilities such as Skills, MCPs, libraries, services, CLIs, GitHub projects, and technical articles. Use for an explicit project tooling inventory/reconcile, tooling/library search, a supplied tool or post…
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, mentions "grill me", or wants one-question-at-a-time clarification where replying 1 accepts the recommended…
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.