Use when the user explicitly wants autonomous progress without routine clarification stops: "plow ahead", "do not stop", "use your best judgment", "keep going until done", "finish while I am away", "do not ask questions unless truly blocked", or similar. Convert ordinary ambiguity into stated assumptions, proceed through implementation and validation, stop only for true blockers, and end with a clear recap of decisions, changes, verification, and residual risk.

Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, inspect what the agent actually changed and verified, report gaps, and optionally make scoped fixes when the user authorizes repair.

Use when writing, fixing, or reviewing Python pytest unit tests, fixtures, mocks, or test PR feedback.

Use when setting up the shared atmosphere-vault Obsidian vault on a new machine or for a new team member. Guides through cloning, symlinking claude_docs, and verifying obsidian-cli.

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

Trigger when the user asks which model to use, wants to compare model costs, says "what's cheapest for this task", "should I use Opus or Sonnet", "can a smaller model handle this", or "/model-cost-compare". Estimates token cost across Opus 4.6, Sonnet 4.6, GLM-5.1, Minimax M2.7, and local Gemma 4, then recommends the cheapest model capable of the task.

Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.

Trigger when the user asks for an architecture diagram, says "draw the system", "update the architecture diagram", "give me an excalidraw of this codebase", or "/excalidraw-architecture". Generates or updates an Excalidraw JSON file at docs/architecture.excalidraw by reading the codebase's key entry points.

Use when you need the current user's identity or contact info: name, job title, employee number, email, phone, or department.

Review new or updated Coral source manifests and source PRs for content, style, product fit, query ergonomics, documentation quality, and consistency with existing Coral sources. Use when Codex is asked to review a sources/core/name or sources/community/name source directory, a manifest.yaml, or a GitHub PR that adds or changes a Coral source.

Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, configuring browser or database persistence, configuring MergeableStore synchronization, or diagnosing an existing TinyBase application.

Use when a Leader must choose Project Work boundaries, owners, dependency shape, DAG vs Loop, acceptance criteria, or follow-up strategy. Do not use for Quick Task execution after the mode is already selected.

Use when a Worker receives TASK_ASSIGNED, acknowledges the task, works inside shared/tasks/{task-id}/, submits with taskflow submit_task, publishes deliverables through submit_task, and reports TASK_COMPLETED or blockers in the Task room.

Use when you are invited to a Project Room or assigned a task within a multi-worker project. Covers project plan reading, task coordination with other Workers, and git author config.

Kode capability-management playbook: treat features (LSP, statusline, output styles, plugins, notifications) as configurable capabilities and drive changes through the agent CLI (SlashCommand/Task) instead of pushing users into menu-like flows. Use when the user asks to enable/disable/configure a capability, diagnose why it’s off, or wants the agent to self-manage Kode’s own features (meta capability management).

Recheck an in-progress App-Store-Connect-CLI pull request for new review feedback, CI results, head changes, and merge readiness. Use when the user says to check for new PR comments, continue polling, fix and loop, babysit a PR, or keep working until the PR is clean.

Publish and verify a new release of the App-Store-Connect-CLI repository. Use only when the user explicitly asks to release, tag, or publish a specific ASC CLI version, including the full GitHub release, artifact, Homebrew, WinGet, cleanup, and release-announcement workflow.

Design, implement, and verify behavior changes in App-Store-Connect-CLI. Use when adding or changing a command, flag, API endpoint, output format, exit code, shared CLI behavior, or when fixing or refactoring behavior that requires code and tests.

Audit App-Store-Connect-CLI pull requests end to end and fix concrete defects. Use when the user asks to audit or review a PR, decide whether a PR is valuable or slop, verify that a PR truly solves its issue, assess blast radius, or make a PR code-ready before merge.

Find businesses, leads, emails, reviews, ratings, and contact details from Google Maps. Use for requests such as "find dentists in Berlin", "scrape Google Maps", "get local business leads", or "collect Google Maps reviews". Runs the open-source scraper locally with Docker and guides nontechnical users through setup, monitoring, and results.