{"owner":"abhigyanpatwari","repo":"GitNexus","hasSkills":true,"hasMcp":false,"mcpConfig":null,"found":["AGENTS.md",".cursorrules",".windsurfrules","CLAUDE.md","llms.txt"],"files":{"AGENTS.md":"<!-- version: 1.14.0 -->\n<!-- Last updated: 2026-07-16 -->\n\nLast reviewed: 2026-07-16\n\n**Project:** GitNexus · **Environment:** dev · **Maintainer:** repository maintainers (see GitHub)\n\n## Scope\n\n| Boundary | Rule |\n|----------|------|\n| **Reads** | `gitnexus/`, `gitnexus-web/`, `eval/`, plugin packages, `.github/`, `.gitnexus/`, docs. |\n| **Writes** | Only paths required for the change; keep diffs minimal. Update lockfiles when deps change. |\n| **Executes** | `npm`, `npx`, `node` under `gitnexus/` and `gitnexus-web/`; `uv run` for Python under `eval/`; documented CI/dev workflows. |\n| **Off-limits** | Real `.env` / secrets, production credentials, unrelated repos, destructive git ops without confirmation. |\n\n## Model Configuration\n\n- **Primary:** Use a named model (e.g. Claude Sonnet 4.x). Avoid `Auto` or unversioned `latest` when reproducibility matters.\n- **Notes:** The GitNexus CLI indexer does not call an LLM.\n\n## Execution Sequence (complex tasks)\n\nFor multi-step work, state up front:\n1. Which rules in this file and **[GUARDRAILS.md](GUARDRAILS.md)** apply (and any relevant Signs).\n2. Current **Scope** boundaries.\n3. Which **validation commands** you will run (`cd gitnexus && npm test`, `npx tsc --noEmit`).\n\nOn long threads, *\"Remember: apply all AGENTS.md rules\"* re-weights these instructions against context dilution.\n\n## Claude Code hooks\n\n**PreToolUse** hooks can block tools (e.g. `git_commit`) until checks pass. Adapt to this repo: `cd gitnexus && npm test` before commit.\n\n## Context budget\n\nCommands and gotchas live under **Repo reference** below and in **[CONTRIBUTING.md](CONTRIBUTING.md)**. If always-on rules grow, split into **`.cursor/rules/*.mdc`** (globs). **Cursor:** project-wide rules in `.cursor/index.mdc`. **Claude Code:** load `STANDARDS.md` only when needed.\n\n## Reference docs\n\n- **[ARCHITECTURE.md](ARCHITECTURE.md)**, **[CONTRIBUTING.md](CONTRIBUTING.md)**, **[GUARDRAILS.md](GUARDRAILS.md)**\n- **Call & inheritance resolution (RFC #909 Ring 3):** See ARCHITECTURE.md § Scope-Resolution Pipeline. All languages resolve calls and inheritance through the scope-resolution pipeline (`Registry.lookup`, `preEmitInheritanceEdges`, `emitHeritageEdges`, `buildMro` → `MethodDispatchIndex`). **Shared code in `gitnexus/src/core/ingestion/` must not name languages** — plug language behavior in via `LanguageProvider` / `ScopeResolver` hooks. A language plugs in by implementing `ScopeResolver` (`scope-resolution/contract/scope-resolver.ts`) and registering it in `SCOPE_RESOLVERS`. (The legacy call-resolution DAG + `@heritage` capture path were removed in RING4-1 #942.)\n- **Cursor:** `.cursor/index.mdc` (always-on); `.cursor/rules/*.mdc` (glob-scoped). Legacy `.cursorrules` deprecated.\n- **GitNexus:** standard skills in `.claude/skills/gitnexus-*/`; MCP rules in `gitnexus:start` block below.\n\n## PR Swarm Review (cross-CLI)\n\nTo run a production-readiness review of a GitNexus pull request from **any** AI CLI, follow\nthe canonical, CLI-neutral spec **[`pr-swarm-review/orchestration.md`](pr-swarm-review/orchestration.md)**\n(seven read-only review personas under `pr-swarm-review/personas/`). It defines two\nexecution modes with the same output contract: **Swarm mode** (parallel subagents, e.g.\nClaude Code) and **Solo mode** (one agent runs all lanes sequentially — Codex, Gemini,\nCursor, Copilot, or any agent reading this file). Per-CLI entrypoints are thin wrappers\nlisted in [`pr-swarm-review/README.md`](pr-swarm-review/README.md); edit review logic only\nin the canonical files, never in the wrappers. The review is read-only — it never edits,\ncommits, or posts.\n\n## Engineering planning & execution (`/gitnexus-plan` · `/gitnexus-work` · `/gitnexus-review` · `/gitnexus-lfg`)\n\nFour canonical, CLI-neutral skill specs under `.claude/skills/` (Claude Code invokes\nthem as slash commands; Codex or any other agent reading this file should read the\nnamed SKILL.md and follow it directly — user-level Codex prompts are documented in the\nplan/work/lfg skill READMEs):\n\n- **`gitnexus-plan/SKILL.md`** — deep, implementation-ready plan for a code change:\n  GitNexus graph intelligence for navigation, statement-level PDG slices for behavioral\n  constraints, targeted source reads for verification. Output lands in `docs/plans/`\n  with a reusable implementation context pack (section 11). Planning-only — it never\n  edits code (index freshness refreshes via `analyze --index-only` are the one\n  permitted state change). Interactive runs ask up front how deep to go\n  (quick / standard / deep); Deepen mode strengthens an existing plan in place.\n- **`gitnexus-work/SKILL.md`** — executes a gitnexus-plan as verified atomic commits:\n  drift-checks the plan's evidence pin against HEAD, `impact` before every symbol\n  edit, tests from the plan's scenarios, `detect_changes` before every commit.\n- **`gitnexus-review/SKILL.md`** — read-only GitNexus review of a PR URL/number,\n  branch or commit range, or local staged/unstaged/untracked changes. It pins exact\n  SHAs, aligns the graph and checkout, runs a PDG-backed taint pass on trust-boundary\n  diffs, scales to per-domain expert lenses from the graph's clusters (dispatched as\n  parallel swarm lanes — `ci-personas/` — when the CI review agent runs it), and\n  reports evidence-backed findings.\n- **`gitnexus-lfg/SKILL.md`** — pipeline orchestrator: plan (depth asked up front) →\n  blocking user gate (proceed or stop) → work → `gitnexus-review`.\n\nThe family ships with the npm package (`gitnexus/skills/`, installed to editor targets\nby `gitnexus setup`) and the Claude Code plugin; review also has a standalone Cursor\nmirror. `gitnexus/test/unit/shipped-skills-sync.test.ts` guards the copies. Token savings of the workflow are measurable with\n`eval/workflow_bench/` (real headless CLI runs, free-model routing supported — see its README).\n\n## Changelog\n\n| Date | Version | Change |\n|------|---------|--------|\n| 2026-07-20 | 1.14.0 | `gitnexus-review` gains a coordinated swarm: six `ci-personas/` lanes the CI review agent dispatches as subagents (via the `Agent` tool), with a bounded critic gate and sidechain-excluded evidence. |\n| 2026-07-16 | 1.13.0 | `gitnexus-plan` asks plan depth up front (quick/standard/deep) in interactive runs; `gitnexus-lfg` gate slimmed to proceed/stop (Deepen stays as the route-back mechanism). |\n| 2026-07-16 | 1.12.0 | Renamed `gitnexus-pr-review` to `gitnexus-review`; added PR URL/number, branch/range, and local-change targets plus install migration (setup warns on a legacy `gitnexus-pr-review` dir and leaves it in place; uninstall removes it). |\n| 2026-07-11 | 1.11.0 | Skill family shipped via npm skills/ + plugin (sync-guarded); added eval/workflow_bench token-savings benchmark. |\n| 2026-07-11 | 1.10.0 | Added `gitnexus-work` (plan executor) and `gitnexus-lfg` (plan → deepen/work gate → review pipeline) skills; section renamed to Engineering planning & execution. |\n| 2026-07-11 | 1.9.0 | Added Engineering planning (`/gitnexus-plan`) section; registered the `gitnexus-plan` skill (`.claude/skills/gitnexus-plan/`). |\n| 2026-05-22 | 1.8.0 | Kotlin added to `MIGRATED_LANGUAGES` (registry-primary call resolution by default). Closes #1756 (companion-vs-instance dispatch) and #1757 (lambda scopes); refs #1746. RFC §6.4 corpus criterion waived (corpus-mode wiring is #927-scope); fixture criterion met. |\n| 2026-04-23 | 1.7.0 | TypeScript added to `MIGRATED_LANGUAGES` (registry-primary call resolution by default). |\n| 2026-04-20 | 1.6.0 | Added scope-resolution pipeline pointer (RFC #909 Ring 3); Python migrated to registry-primary. |\n| 2026-04-19 | 1.5.0 | Cross-repo impact (#794): `impact`/`query`/`context` accept `repo: \"@<group>\"` + `service`. Removed `group_query`/`group_contracts`/`group_status` MCP tools; added `gitnexus://group/{name}/contracts` and `gitnexus://group/{name}/status` resources. |\n| 2026-04-16 | 1.4.0 | Fixed: web UI description, pre-commit behavior, MCP tools (7->16), added gitnexus-shared, removed stale vite-plugin-wasm gotcha. |\n| 2026-04-13 | 1.3.0 | Updated GitNexus index stats after DAG refactor. |\n| 2026-03-24 | 1.2.0 | Fixed gitnexus:start block duplication. |\n| 2026-03-23 | 1.1.0 | Updated agent instructions, references, Cursor layout. |\n| 2026-03-22 | 1.0.0 | Initial structured header and changelog. |\n\n---\n\n<!-- gitnexus:start -->\n# GitNexus — Code Intelligence\n\nThis project is indexed by GitNexus as **GitNexus** (248612 symbols, 565510 relationships, 918 execution flows).\n\n> Index stale? Run `node .gitnexus/run.cjs analyze --index-only` from the project root — it auto-selects an available runner. No `.gitnexus/run.cjs` yet? Bootstrap with `npx`, `bunx`, or `pnpm dlx` — e.g. `bunx gitnexus@latest analyze` (npm 11 npx crash; #1939).\n\n## Always Do\n\n- **MUST run impact analysis before editing.** Use `impact({target: \"symbolName\", direction: \"upstream\"})` (MCP) or `node .gitnexus/run.cjs impact \"symbolName\" --direction upstream --repo .` (CLI fallback); report callers, processes, and risk. Never substitute grep for graph analysis. For unified PDG impact, add `mode: \"pdg\"` with optional `line: <N>` — it returns statement-level `affectedStatements` over CDG + REACHING_DEF and inter-procedural symbols in `interproceduralByDepth`/`byDepth`; no-layer/degraded PDG results are UNKNOWN-risk notes (`--pdg` layer). CLI equivalent: `node .gitnexus/run.cjs impact \"symbolName\" --direction upstream --mode pdg --line <N> --repo .`.\n- **MUST analyze graph changes before committing.** Use `detect_changes({scope: \"all\"})` (MCP) or `node .gitnexus/run.cjs detect-changes --scope all --repo .` (CLI fallback). `partial: true` or `truncated: true` is not a clean check — a zero means unseen, not unaffected; re-run it. For regression review: `detect_changes({scope: \"compare\", base_ref: \"main\"})` or `node .gitnexus/run.cjs detect-changes --scope compare --base-ref \"main\" --repo .`.\n- **MUST warn the user** if impact analysis returns HIGH or CRITICAL risk before proceeding with edits.\n- **MUST treat `risk: UNKNOWN` as unresolved, not as low.** An empty caller set is not evidence the symbol is unused — it can also mean the callers are not resolvable by the index (plain-object property access, dynamic dispatch, cross-language calls). `impact` pairs `UNKNOWN` with a `riskNote` saying so. Confirm with a text search before treating the symbol as safe to change or delete; do not proceed on the strength of a zero.\n- When exploring unfamiliar code, use `query({search_query: \"concept\"})` to find execution flows instead of grepping. It returns process-grouped results ranked by relevance.\n- When you need full context on a specific symbol — callers, callees, which execution flows it participates in — use `context({name: \"symbolName\"})`.\n- For security review, `explain({target: \"fileOrSymbol\"})` lists taint findings (source→sink flows; needs `analyze --pdg`).\n- For control/data dependence, `pdg_query({mode: \"controls\", target: \"fileOrSymbol\"})` answers \"under what condition does X run?\" (CDG, incl. guard clauses) and `pdg_query({mode: \"flows\", target, variable})` traces \"where does variable Y flow?\" (REACHING_DEF). `--pdg` layer.\n\n## Never Do\n\n- NEVER edit a function, class, or method before MCP/CLI impact analysis.\n- NEVER ignore HIGH or CRITICAL risk warnings from impact analysis, and never read `UNKNOWN` as an all-clear — it means the walk could not answer, which is the one verdict that requires confirming by other means.\n- NEVER rename symbols with find-and-replace — use `rename` which understands the call graph.\n- NEVER commit before MCP/CLI graph change analysis.\n\n## Resources\n\n| Resource | Use for |\n| --- | --- |\n| `gitnexus://repo/GitNexus/context` | Codebase overview, check index freshness |\n| `gitnexus://repo/GitNexus/clusters` | All functional areas |\n| `gitnexus://repo/GitNexus/processes` | All execution flows |\n| `gitnexus://repo/GitNexus/process/{name}` | Step-by-step execution trace |\n\n## CLI\n\n| Task | Read this skill file |\n| --- | --- |\n| Understand architecture / \"How does X work?\" | `.claude/skills/gitnexus-exploring/SKILL.md` |\n| Blast radius / \"What breaks if I change X?\" | `.claude/skills/gitnexus-impact-analysis/SKILL.md` |\n| Trace bugs / \"Why is X failing?\" | `.claude/skills/gitnexus-debugging/SKILL.md` |\n| Rename / extract / split / refactor | `.claude/skills/gitnexus-refactoring/SKILL.md` |\n| Tools, resources, schema reference | `.claude/skills/gitnexus-guide/SKILL.md` |\n| Index, status, clean, wiki CLI commands | `.claude/skills/gitnexus-cli/SKILL.md` |\n\n<!-- gitnexus:end -->\n\n## Repo reference\n\n### Packages\n\n| Package | Path | Purpose |\n|---------|------|---------|\n| **CLI/Core** | `gitnexus/` | TypeScript CLI, indexing pipeline, MCP server. Published to npm. |\n| **Web UI** | `gitnexus-web/` | React/Vite thin client. All queries via `gitnexus serve` HTTP API. |\n| **Shared** | `gitnexus-shared/` | Shared TypeScript types and constants. |\n| Claude Plugin | `gitnexus-claude-plugin/` | Static config for Claude marketplace. |\n| Cursor Integration | `gitnexus-cursor-integration/` | Static config for Cursor editor. |\n| Eval | `eval/` | Python evaluation harness (Docker + LLM API keys). |\n\n### Running services\n\n```bash\ncd gitnexus && npm run dev                 # CLI: tsx watch mode\ncd gitnexus-web && npm run dev             # Web UI: Vite on port 5173\nnpx gitnexus serve                         # HTTP API on port 4747 (from any indexed repo)\n```\n\n### Testing\n\n**CLI / Core (`gitnexus/`)**\n- `npm test` — full vitest suite (~2000 tests)\n- `npm run test:unit` — unit tests only\n- `npm run test:integration` — integration (~1850 tests). LadybugDB file-locking tests may fail in containers (known env issue).\n- `npx tsc --noEmit` — typecheck\n\n**Web UI (`gitnexus-web/`)**\n- `npm test` — vitest (~200 tests)\n- `npm run test:e2e` — Playwright (7 spec files; requires `gitnexus serve` + `npm run dev`)\n- `npx tsc -b --noEmit` — typecheck\n\n**Pre-commit hook** (`.husky/pre-commit`): formatting (prettier via lint-staged) + typecheck for staged packages. Tests do **not** run in pre-commit — CI only.\n\n### Gotchas\n\n- `npm install` in `gitnexus/` triggers `prepare` (builds via `tsc`) and `postinstall` (materializes the vendored grammars into `node_modules/`, then prefers a committed prebuild per platform-arch and only source-builds when none matches). A C/C++ toolchain (`python3`, `make`, `g++`) is needed only for that source-build fallback.\n- The vendored grammars `tree-sitter-{c,dart,proto,swift,kotlin}` are handled uniformly: c is required; dart/proto/swift/kotlin are optional and skippable via `GITNEXUS_SKIP_OPTIONAL_GRAMMARS=1`. Install warnings appear only when no prebuild matches the platform-arch and no toolchain is present, and are non-fatal — only that language's parsing is unavailable.\n- ESLint configured via `eslint.config.mjs` (TS, React Hooks, unused-imports). No `npm run lint` script; use `npx eslint .`. Prettier runs via lint-staged. CI checks both in `ci-quality.yml`.\n",".cursorrules":"# Deprecated for Cursor Agent Mode\n\nUse **`.cursor/index.mdc`** (`alwaysApply: true`) for project rules. See [AGENTS.md](AGENTS.md).\n\nThis file is kept only as a breadcrumb for older workflows.\n",".windsurfrules":"# AI Agent Rules\n\nFollow .gitnexus/RULES.md for all project context and coding guidelines.\n\nThis project uses GitNexus MCP for code intelligence. See .gitnexus/RULES.md for available tools and best practices.\n","CLAUDE.md":"<!-- version: 1.8.0 -->\n<!--\n  Metadata: version, last reviewed, scope, model policy, reference docs, changelog.\n  Last updated: 2026-07-16\n-->\n\nLast reviewed: 2026-07-16\n\n**Project:** GitNexus · **Environment:** dev · **Maintainer:** repository maintainers (see GitHub)\n\nFollow **AGENTS.md** for the canonical rules; this file adds Claude Code–specific deltas. Cursor-specific notes live only in `AGENTS.md`.\n\n## Scope\n\nSee the **Scope** table in [AGENTS.md](AGENTS.md) for read/write/execute/off-limits boundaries. Cursor-specific workflow notes also live only in AGENTS.md.\n\n## Model Configuration\n\n- **Primary:** Pin per **Claude Code** / Anthropic org policy (explicit model id). Do not rely on an unversioned `latest` alias for governed workflows.\n- **Fallback:** As configured in Claude Code (organization default or user override).\n- **Notes:** The GitNexus CLI analyzer does not call an LLM.\n\n## Execution Sequence (complex tasks)\n\nSame discipline as [AGENTS.md](AGENTS.md): before large multi-step work, state which **AGENTS.md** / **GUARDRAILS.md** rules apply, current **Scope**, and planned validation commands (`npm test`, `tsc`, etc.). When pausing, summarize progress in the chat or a **local** scratch file (do not add `HANDOFF.md` to the repo), then `/clear` and resume with that summary.\n\n## Claude Code hooks\n\nPrefer **PreToolUse** hooks for hard gates (e.g. tests before `git_commit`). Adapt hook commands to `gitnexus/` npm scripts.\n\n## Context budget\n\nIf always-on instructions grow, load deep conventions via conditional reads (e.g. *“When writing new code, read STANDARDS.md”*) instead of pasting long blocks here. In Cursor, prefer `.cursor/index.mdc` plus optional `.cursor/rules/*.mdc` globs (see [AGENTS.md](AGENTS.md) § Context budget).\n\n## Reference Documentation\n\n- **This repository:** [AGENTS.md](AGENTS.md) (Cursor + monorepo notes), [ARCHITECTURE.md](ARCHITECTURE.md), [CONTRIBUTING.md](CONTRIBUTING.md), [GUARDRAILS.md](GUARDRAILS.md).\n- **Call & inheritance resolution:** See ARCHITECTURE.md § Scope-Resolution Pipeline. Shared pipeline code in `gitnexus/src/core/ingestion/` must not name languages — use `LanguageProvider` / `ScopeResolver` hooks instead (see AGENTS.md). (The legacy call-resolution DAG was removed in #942.)\n- **GitNexus:** standard skills in `.claude/skills/gitnexus-*/`; MCP and indexed-repo rules live only in [AGENTS.md](AGENTS.md) (`gitnexus:start` … `gitnexus:end`). See **GitNexus rules** below.\n- **Engineering plans, execution & review:** `/gitnexus-plan <task>` (implementation-ready plans via GitNexus + statement-level PDG + source verification; Deepen mode for existing plans), `/gitnexus-work [plan]` (executes a plan as impact-checked, detect_changes-gated atomic commits), `/gitnexus-review [PR|branch|range|local]` (read-only graph-backed review), `/gitnexus-lfg <task>` (plan with depth asked up front → proceed/stop gate → work → review pipeline). Specs in `.claude/skills/gitnexus-{plan,work,review,lfg}/SKILL.md` (see AGENTS.md § Engineering planning & execution).\n\n## Changelog\n\n| Date | Version | Change |\n|------|---------|--------|\n| 2026-07-20 | 1.8.0 | The CI review agent runs `gitnexus-review` as a coordinated swarm — six `ci-personas/` lanes dispatched via the `Agent` tool with a bounded critic gate. |\n| 2026-07-16 | 1.7.0 | `/gitnexus-plan` asks depth up front in interactive runs; `/gitnexus-lfg` gate slimmed to proceed/stop. |\n| 2026-07-16 | 1.6.0 | Renamed `/gitnexus-pr-review` to `/gitnexus-review` and added PR, branch/range, and local-change targets. |\n| 2026-07-11 | 1.5.0 | Added `/gitnexus-work` and `/gitnexus-lfg` to the engineering plans & execution pointer. |\n| 2026-07-11 | 1.4.0 | Added `/gitnexus-plan` pointer to Reference Documentation. |\n| 2026-04-13 | 1.3.0 | Updated GitNexus index stats after DAG refactor. |\n| 2026-03-24 | 1.2.0 | Removed duplicated gitnexus:start block and scope table; replaced with pointers to AGENTS.md. |\n| 2026-03-23 | 1.1.0 | Updated agent instructions to match AGENTS.md. |\n| 2026-03-22 | 1.0.0 | Added structured header and changelog. |\n\n---\n\n## GitNexus rules\n\nSee the `<!-- gitnexus:start --> … <!-- gitnexus:end -->` block in **[AGENTS.md](AGENTS.md)** for the canonical MCP tools, impact analysis rules, and index instructions.\n\n<!-- gitnexus:start -->\n# GitNexus — Code Intelligence\n\nThis project is indexed by GitNexus as **GitNexus** (248612 symbols, 565510 relationships, 918 execution flows).\n\n> Index stale? Run `node .gitnexus/run.cjs analyze --index-only` from the project root — it auto-selects an available runner. No `.gitnexus/run.cjs` yet? Bootstrap with `npx`, `bunx`, or `pnpm dlx` — e.g. `bunx gitnexus@latest analyze` (npm 11 npx crash; #1939).\n\n## Always Do\n\n- **MUST run impact analysis before editing.** Use `impact({target: \"symbolName\", direction: \"upstream\"})` (MCP) or `node .gitnexus/run.cjs impact \"symbolName\" --direction upstream --repo .` (CLI fallback); report callers, processes, and risk. Never substitute grep for graph analysis. For unified PDG impact, add `mode: \"pdg\"` with optional `line: <N>` — it returns statement-level `affectedStatements` over CDG + REACHING_DEF and inter-procedural symbols in `interproceduralByDepth`/`byDepth`; no-layer/degraded PDG results are UNKNOWN-risk notes (`--pdg` layer). CLI equivalent: `node .gitnexus/run.cjs impact \"symbolName\" --direction upstream --mode pdg --line <N> --repo .`.\n- **MUST analyze graph changes before committing.** Use `detect_changes({scope: \"all\"})` (MCP) or `node .gitnexus/run.cjs detect-changes --scope all --repo .` (CLI fallback). `partial: true` or `truncated: true` is not a clean check — a zero means unseen, not unaffected; re-run it. For regression review: `detect_changes({scope: \"compare\", base_ref: \"main\"})` or `node .gitnexus/run.cjs detect-changes --scope compare --base-ref \"main\" --repo .`.\n- **MUST warn the user** if impact analysis returns HIGH or CRITICAL risk before proceeding with edits.\n- **MUST treat `risk: UNKNOWN` as unresolved, not as low.** An empty caller set is not evidence the symbol is unused — it can also mean the callers are not resolvable by the index (plain-object property access, dynamic dispatch, cross-language calls). `impact` pairs `UNKNOWN` with a `riskNote` saying so. Confirm with a text search before treating the symbol as safe to change or delete; do not proceed on the strength of a zero.\n- When exploring unfamiliar code, use `query({search_query: \"concept\"})` to find execution flows instead of grepping. It returns process-grouped results ranked by relevance.\n- When you need full context on a specific symbol — callers, callees, which execution flows it participates in — use `context({name: \"symbolName\"})`.\n- For security review, `explain({target: \"fileOrSymbol\"})` lists taint findings (source→sink flows; needs `analyze --pdg`).\n- For control/data dependence, `pdg_query({mode: \"controls\", target: \"fileOrSymbol\"})` answers \"under what condition does X run?\" (CDG, incl. guard clauses) and `pdg_query({mode: \"flows\", target, variable})` traces \"where does variable Y flow?\" (REACHING_DEF). `--pdg` layer.\n\n## Never Do\n\n- NEVER edit a function, class, or method before MCP/CLI impact analysis.\n- NEVER ignore HIGH or CRITICAL risk warnings from impact analysis, and never read `UNKNOWN` as an all-clear — it means the walk could not answer, which is the one verdict that requires confirming by other means.\n- NEVER rename symbols with find-and-replace — use `rename` which understands the call graph.\n- NEVER commit before MCP/CLI graph change analysis.\n\n## Resources\n\n| Resource | Use for |\n| --- | --- |\n| `gitnexus://repo/GitNexus/context` | Codebase overview, check index freshness |\n| `gitnexus://repo/GitNexus/clusters` | All functional areas |\n| `gitnexus://repo/GitNexus/processes` | All execution flows |\n| `gitnexus://repo/GitNexus/process/{name}` | Step-by-step execution trace |\n\n## CLI\n\n| Task | Read this skill file |\n| --- | --- |\n| Understand architecture / \"How does X work?\" | `.claude/skills/gitnexus-exploring/SKILL.md` |\n| Blast radius / \"What breaks if I change X?\" | `.claude/skills/gitnexus-impact-analysis/SKILL.md` |\n| Trace bugs / \"Why is X failing?\" | `.claude/skills/gitnexus-debugging/SKILL.md` |\n| Rename / extract / split / refactor | `.claude/skills/gitnexus-refactoring/SKILL.md` |\n| Tools, resources, schema reference | `.claude/skills/gitnexus-guide/SKILL.md` |\n| Index, status, clean, wiki CLI commands | `.claude/skills/gitnexus-cli/SKILL.md` |\n\n<!-- gitnexus:end -->\n","llms.txt":"GitNexus monorepo (CLI + web UI)\n\n# Core docs (read first for any contribution)\n- AGENTS.md — canonical agent instructions, GitNexus MCP tool reference\n- GUARDRAILS.md — non-negotiables and escalation triggers\n\n# Operational (read when running commands or debugging)\n- RUNBOOK.md — copy-paste commands for common workflows\n- TESTING.md — test commands for both packages\n- CONTRIBUTING.md — contribution workflow and PR conventions\n\n# Architecture (read for design context)\n- ARCHITECTURE.md — system overview, data flow, component relationships\n\n# Key directories\n- gitnexus/ (CLI/core, MCP server — TypeScript)\n- gitnexus-web/ (web UI — React/Vite/WASM)\n- eval/ (SWE-bench evaluation harness — Python)\n- gitnexus-claude-plugin/ (Claude marketplace config)\n- gitnexus-cursor-integration/ (Cursor integration config)\n"}}