How do I install the Anvien CLI skill?

Run npx skillmds@latest add tamnguyendinh/anvien-cli in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Anvien CLI safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Anvien CLI?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Anvien CLI free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Anvien CLI?

tamnguyendinh (@tamnguyendinh) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Anvien CLI by tamnguyendinh — Agent Skill

Name: Anvien CLI
Author: tamnguyendinh

Anvien CLI

Use when the user needs to run Anvien CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"

tamnguyendinh 95d9a8d 2 files · 2.8 KB Updated Sep 17, 2026

File contents

Anvien CLI Commands

All commands work via npx — no global install required.

Commands

analyze — Build or refresh the index

anvien analyze

Run from the project root. This parses all source files, builds the knowledge graph, writes it to .anvien/, and generates CLAUDE.md / AGENTS.md context files.

Flag	Effect
`--force`	Force full re-index even if up to date
`--embeddings`	Enable embedding generation for semantic search (off by default)

When to run: First time in a project, after major code changes, or when anvien://repo/{name}/context reports the index is stale.

status — Check index freshness

anvien status

Shows whether the current repo has a Anvien index, when it was last updated, and symbol/relationship counts. Use this to check if re-indexing is needed.

clean — Delete the index

anvien clean

Deletes the .anvien/ directory and unregisters the repo from the global registry. Use before re-indexing if the index is corrupt or after removing Anvien from a project.

Flag	Effect
`--force`	Skip confirmation prompt
`--all`	Clean all indexed repos, not just the current one

wiki — Generate documentation from the graph

anvien wiki

Runs the local wiki capability for the current repository. Check the current wiki mode first; local-only mode must not fall back to remote providers.

Flag	Effect
`--force`	Force full regeneration
`--model <model>`	LLM model (default: minimax/minimax-m2.5)
`--base-url <url>`	LLM API base URL
`--api-key <key>`	LLM API key
`--concurrency <n>`	Parallel LLM calls (default: 3)
`--gist`	Publish wiki as a public GitHub Gist

list — Show all indexed repos

anvien list

Lists all repositories registered in ~/.anvien/registry.json. The MCP list_repos tool provides the same information.

After Indexing

Read anvien://repo/{name}/context to verify the index loaded
Use the other Anvien skills (exploring, debugging, impact-analysis, refactoring) for your task

Troubleshooting

"Not inside a git repository": Run from a directory inside a git repo
Index is stale after re-analyzing: Restart Claude Code to reload the MCP server
Embeddings slow: Omit --embeddings (it's off by default) or set OPENAI_API_KEY for faster API-based embedding

---name: anvien-clidescription: Use when the user needs to run Anvien CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"---# Anvien CLI CommandsAll commands work via `npx` — no global install required.## Commands### analyze — Build or refresh the index```bashanvien analyze```Run from the project root. This parses all source files, builds the knowledge graph, writes it to `.anvien/`, and generates CLAUDE.md / AGENTS.md context files.| Flag | Effect ||------|--------|| `--force` | Force full re-index even if up to date || `--embeddings` | Enable embedding generation for semantic search (off by default) |**When to run:** First time in a project, after major code changes, or when `anvien://repo/{name}/context` reports the index is stale.### status — Check index freshness```bashanvien status```Shows whether the current repo has a Anvien index, when it was last updated, and symbol/relationship counts. Use this to check if re-indexing is needed.### clean — Delete the index```bashanvien clean```Deletes the `.anvien/` directory and unregisters the repo from the global registry. Use before re-indexing if the index is corrupt or after removing Anvien from a project.| Flag | Effect ||------|--------|| `--force` | Skip confirmation prompt || `--all` | Clean all indexed repos, not just the current one |### wiki — Generate documentation from the graph```bashanvien wiki```Runs the local wiki capability for the current repository. Check the current wiki mode first; local-only mode must not fall back to remote providers.| Flag | Effect ||------|--------|| `--force` | Force full regeneration || `--model <model>` | LLM model (default: minimax/minimax-m2.5) || `--base-url <url>` | LLM API base URL || `--api-key <key>` | LLM API key || `--concurrency <n>` | Parallel LLM calls (default: 3) || `--gist` | Publish wiki as a public GitHub Gist |### list — Show all indexed repos```bashanvien list```Lists all repositories registered in `~/.anvien/registry.json`. The MCP `list_repos` tool provides the same information.## After Indexing1. **Read `anvien://repo/{name}/context`** to verify the index loaded2. Use the other Anvien skills (`exploring`, `debugging`, `impact-analysis`, `refactoring`) for your task## Troubleshooting- **"Not inside a git repository"**: Run from a directory inside a git repo- **Index is stale after re-analyzing**: Restart Claude Code to reload the MCP server- **Embeddings slow**: Omit `--embeddings` (it's off by default) or set `OPENAI_API_KEY` for faster API-based embedding

Frequently asked questions