Loctree

Loctree/loctree

Instructions file GitHub Copilot

Official Copilot instructions for the Loctree project.

Loctree/loctree

Instructions file CodexOpenCode

AGENTS.md instructions for Loctree/loctree, covering vetcoders agent operating guide v1, loctree operating rule, recommended daily order, before editing and literal truth before assumptions.

Loctree/loctree

Hook

Runs before the context is compacted, executing aicx-precompact.sh. From Loctree/loctree.

Loctree/loctree

Hook

Runs when a session starts on compact, executing aicx-postcompact.sh. From Loctree/loctree.

Loctree/loctree

Plugin Claude Code

CANONICAL loctree agent plugin (suite). Structural perception — slice before edit, impact before delete, find before create (incl. multi-literal OR A|B on MCP/LSP/CLI), prism before vc-polarize. Powered by loctree-mcp + loctree-lsp. Deprecated peer path: suite ./plugin/ (redirect only).

Loctree/loctree

MCP server Claude CodeCodexCursor +2

MCP server "loctree-mcp" as configured in Loctree/loctree. Launched with loctree-mcp.

Loctree/loctree

MCP server Claude CodeCodexCursor +2

MCP server "loctree-lsp" as configured in Loctree/loctree. Launched with loctree-lsp.

Loctree/loctree

Agent

Use this agent immediately before performing an Edit, Write, or MultiEdit on a non-trivial source file when the parent agent needs structural orientation it doesn't have. Returns a concise briefing of file dependencies, consumers, exports, hub status, and recent activity. Trigger when the user says "before I edit X…

Loctree/loctree

Agent

Use this agent BEFORE planning a refactor — module split, module merge, signature change to a public API, file rename, dependency direction reversal, framework migration. Returns a migration plan with: blast radius (transitive consumers), twins to consolidate or split, hotspots that must be touched together, cycles…

Loctree/loctree

Agent

Use this agent for senior-level structural review of a codebase or a specific change set, focused on architectural integrity rather than line-level style. Trigger when the user asks for "structural review", "architecture audit", "senior review", "is this well-designed", "review this refactor", "/structural-review"…

Loctree/loctree

Skill Claude CodeCodex

Materialize the loctree Context Atlas — six cards (core, structural, runtime, memory-trail, verification-gates, risk-register) — for the current project. Use at session start, after clear / compact, when entering an unfamiliar repo, when planning a refactor, or whenever the agent needs full structural orientation in…

Loctree/loctree

Skill Claude CodeCodex

Find exact identifier occurrences, definition/re-export sites, reverse imports, or broad discovery candidates. Use before creating symbols and when separating literal evidence from structural or fuzzy discovery.

Loctree/loctree

Skill Claude CodeCodex

Deep-dive on a directory or module — files, internal edges, external dependencies, LOC. Use when entering an unfamiliar module, mapping a sub-system before refactor, or evaluating module cohesion. Triggers on phrases "focus on this module", "map this directory", "show me the auth module", "/loctree:focus", "what's in…

Loctree/loctree

Skill Claude CodeCodex

Pursue structural signals — dead code, cycles, duplicate exports (twins), hotspots, runtime traces, command/event/pipeline graphs. Use during cleanup, audit, refactor planning, or when investigating "is this used?" questions at module/system scope. Triggers on phrases "follow signals", "find dead code", "find cycles"…

Loctree/loctree

Skill Claude CodeCodex

Compute direct AND transitive consumers (full blast radius) of a file before deletion, rename, or breaking signature change. Use BEFORE any git rm, git mv, public API rename, or large signature change. Triggers on phrases "impact of this file", "blast radius", "what breaks if I remove", "before I delete", "transitive…

Loctree/loctree

Skill Claude CodeCodex

Score conceptual smear (drift, spread, runtime centrality, authority diversity, drift risk, closure evidence) across two or more task framings on the canonical 0..15 rubric. Use BEFORE running vc-polarize, BEFORE choosing a doctrine cut, or whenever an agent needs structural evidence for the abort/memo/pass/doctrine…

Loctree/loctree

Skill Claude CodeCodex

One-shot repository overview — file count, LOC by language, top hubs, health summary. Use at first contact with an unfamiliar repo, when the agent needs the 30-second elevator pitch of "what is this codebase". Triggers on phrases "repo overview", "what is this repo", "/loctree:repo-view", "loct repo-view", "show me…

Loctree/loctree

Skill Claude CodeCodex

Surface a single file's dependencies, consumers, exports, and structural neighborhood before any modification. Use BEFORE every Edit, Write, or refactor on a source file. Triggers on phrases "slice this file", "what depends on", "before I edit", "show file dependencies", "/loctree:slice", "what consumes this"…

Loctree/loctree

Skill Claude CodeCodex

Render directory structure with LOC counts per file/dir. Use when the agent needs to understand the physical layout of the codebase, where files live, depth of nesting, and which dirs are heavy. Triggers on phrases "show directory tree", "/loctree:tree", "loct tree", "directory structure", "where is the code", "repo…

Loctree/loctree

Skill Claude CodeCodex

Structural and literal repository perception before edits, deletes, refactors, or unfamiliar-code work. Use context/repo-view/focus/slice/impact/find/follow to establish scope, dependencies, blast radius, exact occurrences, and analyzer coverage before acting.

Loctree/loctree

Plugin Claude Code

DEPRECATED stub. Canonical Claude/Codex agent plugin is loctree-suite/loctree-plugin/. Do not install this path.