Menu
Use when a task needs structural/relational code navigation — call graph, references, blast-radius, trace flows, safe refactors — and the GitNexus plugin is enabled. Routes intent to the native gitnexus-* skills.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Consolidated view of the add-pro ecosystem - commands, skills, relationships and dependencies. Loaded by /add as source of truth.
Source of truth for ADD doc rules, depth floors, IDs, refs, validation gate. Load before any doc write.
Use when running agent-judged QA validation (read-PNG by default; the playwright plugin adds live driving) — the Level C judge rubric, severity taxonomy, dual-judge (@ux-agent review ∥ @qa-agent) method, report schema/template, and the config.json/screens.json formats. Consumed by /add.qa and both judges.
Use when a state-materializing command starts or is asked to upgrade — reads the setup receipt, compares the recorded contract against the shipped one, executes the declared upgrade deltas sequentially, and rewrites the receipt even on a verified-current no-op. Consumed by /add.qa-setup STEP 1.5 and STEP 11.
Internal skill for developing ADD framework artefacts (commands, skills, agents, scripts). Use when add-framework--plan analyzes viability of new framework features, when add-framework--build implements framework artefacts, or when creating/modifying commands, skills, or agents. Always use this skill before proposing or implementing changes to the framework itself.
Use when building, styling, or theming UI components, pages, layouts, dashboards, charts, tables, or forms for SaaS products.
Based on SOC occupation classification
| name | add-gitnexus |
| description | Use when a task needs structural/relational code navigation — call graph, references, blast-radius, trace flows, safe refactors — and the GitNexus plugin is enabled. Routes intent to the native gitnexus-* skills. |
GitNexus exposes a code knowledge-graph (calls, refs, blast-radius) over MCP, with native gitnexus-* skills that already document how to use each tool. This skill is a thin dispatcher: it maps the current intent to the right native skill. It does not reimplement MCP tools and has no fallback branch — when an intent matches, load the native skill and follow it.
GitNexus indexes repositories by name and serves them all from one MCP instance. When more than one repo is indexed, every tool (query, context, impact, route_map, …) requires a repo parameter — omitting it fails with:
Error: Multiple repositories indexed. Specify which one with the "repo" parameter. Available: ...
Before the first gitnexus MCP call in a task, resolve the repo once:
list_repos.repo (single-repo calls need no disambiguation).path equals the current repo root (git rev-parse --show-toplevel);
b. else the path basename equals the repo-root basename (handles WSL/Windows path mismatch, e.g. /mnt/c/... vs C:\...);
c. else the repo-root basename matches the git remote slug (git remote get-url origin);
d. else ask the user which of the listed names to use — do not guess.name as repo on every gitnexus tool call for the rest of the task.Zero repos → the project is unindexed: say so explicitly and fall back to grep (see Operating note).
| Agent intent | Load native skill |
|---|---|
| Map architecture, "how does X work", "what calls X", trace flow | gitnexus-exploring |
| Blast-radius, "what breaks if I change X", safe-to-edit | gitnexus-impact-analysis |
| Trace an error, "why does X fail" | gitnexus-debugging |
| Rename / extract / split / move safely | gitnexus-refactoring |
| Review a PR, assess merge risk | gitnexus-pr-review |
| Run GitNexus CLI (index / status / wiki) | gitnexus-cli |
| Graph schema / available tools | gitnexus-guide |
When reached from a codeadd command, resolve as:
add.new (discovery) → gitnexus-exploring — map modules, key call paths, entry points before questioning.add.plan (planning) → gitnexus-impact-analysis — establish blast-radius (callers, dependents, dead-code) of the change surface before dispatching subagents.add.diagnose (triage) → gitnexus-impact-analysis for blast-radius, or gitnexus-debugging to trace an error to its source.add.hotfix (pre-edit) → gitnexus-impact-analysis — find impacted call sites of the symbol about to change.add.done (post-change) → gitnexus-cli — re-index (gitnexus analyze) after significant changes so the graph stays current.This skill assumes an indexed graph. Freshness is handled at add.done (re-index after significant changes), not here. If the graph returns nothing, the repo may be unindexed — say so explicitly, then proceed with grep; do not block.