Audit stored normal content on the bound Context Tree's actual binding branch when a human explicitly asks to audit the whole tree, a domain, or specific normal paths for drift, contradictions, duplication, density, metadata, placement, or relationship problems. Do not use for ordinary task reads, source-backed writes, Context Tree PR/MR reviews, or empty-tree setup.

Review a GitHub pull request or GitLab merge request against the workspace-bound Context Tree when a trusted server-authored Context Reviewer run supplies provider-scoped authority. Repair every safely determined finding with the host git and forge CLI identity, then use GitHub App review plus exact-head merge or GitLab note plus exact-SHA merge. Do not use for code changes, ordinary tree reads or writes, or default-branch audits.

This is the entry-point skill for the `first-tree` toolkit. It teaches:

Read this skill **before** drafting the first content into a Context Tree that has no domain structure yet. It owns the bootstrap from "the tree has no domain structure — either none exists, or a bound-but-empty one" to "the tree has real top + second level structure plus initial leaf nodes drawn

Context Tree concepts and routing sub-entry. Explains what a Context Tree is, the ownership model, what belongs in a node vs. a source system, and how to navigate domains and soft_links. Use whenever you need shared Context Tree concepts, are unsure whether your task is onboarding / sync / write, or need the structural primer before acting on the tree. For binding a repo, use `first-tree-onboarding`; for drift audit, `first-tree-sync`; for writing from a specific source, `first-tree-write`.

Agent skill for handling a single GitHub notification inside the First Tree github-scan daemon path. Use when an agent needs to decide how to tag, comment on, escalate, or hand off a PR, issue, review request, mention, or CI event, and when it needs to decide whether to involve a human or trigger `first-tree-sync` or `first-tree-write`. This is not the human CLI operations guide for the daemon.

Onboard a repo or workspace to First Tree using the current CLI surface and the proposal-aligned five-step setup flow. Use when a repo is unbound, when a workspace needs a shared tree, when you need to choose between creating a new tree and binding an existing one, or when you need to install or start the GitHub scan daemon and prepare agent templates.

Read the current repo's Context Tree before acting. Use when the user provides a task, topic, file path, feature name, bug, error, repo area, owner, or other signal and Codex needs to locate and read the relevant context files from the bound context repo. Always inspect `first-tree tree tree --help` in the context repo first, then use `first-tree tree tree` filtering options to select candidate files; read the selected file contents with the agent's native file-reading capability.

Write Context Tree updates from explicit source material such as code PRs, design docs, meeting notes, or raw text. Use when the user gives you concrete inputs and wants the right durable tree changes drafted, linked, and reviewed. This skill is source-driven and targeted; use `first-tree-sync` instead for broad drift audits.