Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.

Apache-2.0Auto-check passedAgent Workflows

Install Ix

skills CLI
$ npx skills add ix-infrastructure/Ix --skill ix -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ix-infrastructure/Ix ix --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ix-infrastructure/Ix.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ix .claude/skills/ix && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ix
GitHub stars
1k
Token cost
~1.2k tokens
SKILL.md length
673 words
Files
7 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0

At a glance

Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.

  • Works in 5 steps: Start with ix context — one bounded call… → Read the ranges, not the files. ix read… → Ask the graph what grep cannot: ix… → …
  • Agent Workflows work in your project
  • SKILL.md covers First run, Core workflow, Over MCP and How to spend calls, plus 2 more sections
  • Runs PowerShell and Shell scripts from its folder; calls bash

What it does

Ix is an agent skill from ix-infrastructure/Ix. Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `references/commands.md`, `references/flags.md` and `references/output-formats.md`).

It sits in Agent Workflows. It works with Model Context Protocol. The repository describes itself as: Understand any codebase instantly. System intelligence for codebases, built for humans and AI. The licence is Apache-2.0.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “/ix”

Requirements

  • A Bash shell
  • PowerShell
  • Docker

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Start with ix context — one bounded call that names the
  2. Read the ranges, not the files. ix read , or path:120-180, is
  3. Ask the graph what grep cannot: ix callers, ix imported-by and
  4. Do not poll ix status. A command that needs the backend says so itself,
  5. Format: llm is the one to read, and IX_FORMAT=llm (or

What it can do on your machine

Read from SKILL.md and the folder at commit 74499ba. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (PowerShell and Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ix loads about 1.2k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 49 tokens; SKILL.md has 673 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~18k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ix-infrastructure/Ix at commit 74499ba, republished under its Apache-2.0 licence (© ix-infrastructure). 673 words, ~1,249 tokens.

Download SKILL.mdSave it as .claude/skills/ix/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
ix
description
Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.
license
Apache-2.0
metadata.version
1.0.0
metadata.source
https://github.com/ix-infrastructure/Ix

Ix — Persistent Codebase Map

Ix parses a repository with tree-sitter (27 languages) into a graph of symbols, calls and imports, kept in a local backend (ArangoDB via Docker) and persisted between sessions. Query it for structural answers — what a symbol is, what calls it, how a flow moves, what a change breaks, which files carry the most weight, where the smells are — instead of reading files to find out. It does not answer prose or history questions.

First run

bash
bash scripts/bootstrap.sh [repo-root] [--no-map]                                     # macOS / Linux / Git Bash
powershell -ExecutionPolicy Bypass -File scripts/bootstrap.ps1 [repo-root] [-NoMap]  # Windows

Checks Node >= 22, git, Docker and ripgrep, installs the CLI if missing, starts the backend, and maps the repo. Re-run it per repo.

Core workflow

StepCommandExample
Bounded context to start fromix contextix context IngestionService
Start from an issue or bug reportix context --from-issueix context --from-issue issue.md (or - for stdin)
Understand a componentix explainix explain IngestionService
Trace a flowix traceix trace user_login_flow
Blast radius of a changeix impactix impact verify_token

Over MCP

When the ix-memory MCP server is connected (ix mcp; register it with ix mcp install), the same graph is five tools. Reach for them where Grep, Glob and Read need several steps or cannot answer at all:

QuestionTool
Where to start on an issue or task; what a file or symbol touchesix_context target=<name or path> or ix_context issue=<issue text>
Who calls / is called by / imports / is imported by X, across filesix_neighbors symbol=X relation=callers|callees|imports|imported_by
What a change to X reaches, before editing itix_impact target=X
Which definition a name means when several share itix_search term=X
A definition's source by name, without knowing its fileix_read symbol=X

Not for a literal string or a line in a file you already have open: that is Grep and Read. ix_context and ix_impact end in next records phrased as tool calls; an ambiguous name answers with candidates and pick=/path= to choose one. No health check is needed first. ix mcp --tools=all serves every command as a tool.

Show full SKILL.md (345 more words)Show less

How to spend calls

  1. Start with ix context <file-or-symbol> — one bounded call that names the files and symbols that matter, with line ranges.
  2. Read the ranges, not the files. ix read <symbol>, or path:120-180, is one to three thousand tokens; the file around it is commonly thirty to sixty thousand — and every one of those is re-sent on every later step of the turn.
  3. Ask the graph what grep cannot: ix callers, ix imported-by and ix impact answer "who uses this" and "what does a change reach" across files. Drill further with ix search, ix callees, ix contains, ix imports, ix depends, reusing the exact entity IDs from earlier output.
  4. Do not poll ix status. A command that needs the backend says so itself, with a hint; a health check in front of every call is a wasted round trip.
  5. Format: llm is the one to read, and IX_FORMAT=llm (or ix config set format llm) makes it the default so it need not be typed per call; json is for chaining or extracting a field. On ix context the same answer runs about 7.6 : 0.8 : 1 for json : llm : text.

Rules

  1. Answer codebase questions from targeted ix commands, not from training data.
  2. Never guess a codebase fact that Ix holds.
  3. The graph is kept current for you: bootstrap maps the repo and editor plugins re-ingest edited files. Run ix map --silent only when results are visibly stale, such as after a branch switch or a pull.
  4. When Ix reports low confidence, say so, and never present it as established fact.

References — load on demand

  • references/commands.md — command routing tables, decomposition recipes, best practices, the do-not-use list. Before any command beyond the table above.
  • references/flags.md — every flag the CLI registers, per command, with values and defaults. Before guessing whether a flag exists.
  • references/output-formats.md — the llm|json|text rules, what does not implement llm, and which commands are Pro-gated.
  • references/troubleshooting.md — prerequisites, ix doctor, backend health, environment flags. When a command fails.
  • scripts/bootstrap.sh / scripts/bootstrap.ps1 — first-run setup (bash; and native PowerShell for Windows).

© ix-infrastructure, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (scripts, references) in skills/ix of ix-infrastructure/Ix.

  • SKILL.md
  • references/commands.md
  • references/flags.md
  • references/output-formats.md
  • references/troubleshooting.md
  • scripts/bootstrap.ps1
  • scripts/bootstrap.sh

Open the folder on GitHubat commit 74499ba

Compare with similar skills

Ix next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ix this skillix-infrastructure/Ix1k—~1.2kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Orca Run Replayiflytek/skillhub5.2k4 repos~3kAutomated safety check: PassApache-2.0
PicoClaw Agentsipeed/picoclaw30k—~7.2kAutomated safety check: NotesMIT
Chatgpt AppsHaohao-end/openagent8071 repos~4.9kAutomated safety check: PassApache-2.0
Chatgpt App Builderalpic-ai/skybridge2.1k—~1kAutomated safety check: PassMIT

Similar skills

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Orca Run Replay

    iflytek/skillhub

    Answers questions about a past agent run from its recording, using causal graphs and replay, instead of reconstructing events from memory.

    5.2k GitHub starsUsed in 4 repos~3k tokens
    Agent WorkflowsAuto-check passed
  • PicoClaw Agent

    sipeed/picoclaw

    Answers questions about running and changing PicoClaw, from onboarding and model selection to MCP server setup, skill loading and scheduled jobs.

    30k GitHub stars~7.2k tokensUpdated 13 days ago
    Agent WorkflowsAuto-check: notes
  • Chatgpt Apps

    Haohao-end/openagent

    Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI.

    807 GitHub starsUsed in 1 repo~4.9k tokens
    Agent WorkflowsAuto-check passed
  • Chatgpt App Builder

    alpic-ai/skybridge

    Guide developers through creating and updating ChatGPT plugins.

    2.1k GitHub stars~1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Audits a project's agent configuration, instruction drift, hooks, MCP and AI maintainability, then reports prioritized findings with evidence and next actions.

    7.2k GitHub stars~5.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes

Questions about Ix

What does Ix do?

Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping. Ix is an agent skill from ix-infrastructure/Ix. Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.

When should I use Ix?

Ix fits situations like: agent Workflows work in your project.

How do I install Ix in Claude Code?

Run `npx skills add ix-infrastructure/Ix --skill ix -a claude-code`. Or copy the skill folder (skills/ix in ix-infrastructure/Ix) into .claude/skills/ix in your project. Claude Code loads it when a task matches its description.

How do I install Ix in Codex?

Run `npx skills add ix-infrastructure/Ix --skill ix -a codex`. Or copy the skill folder (skills/ix in ix-infrastructure/Ix) into .agents/skills/ix in your project. Codex loads it when a task matches its description.

Can I use Ix in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ix-infrastructure/Ix --skill ix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ix, .gemini/skills/ix, .github/skills/ix and .opencode/skills/ix in your project.

What does Ix need to run?

Going by SKILL.md and its folder, Ix needs PowerShell and a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: A Bash shell; PowerShell; Docker.

Does Ix access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ix safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Ix use?

Ix is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ix use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 17k tokens, read only when the agent opens those files.

What are the alternatives to Ix?

Skills that share tags, products or a category with Ix: Crush Configuration (charmbracelet/crush, 29k stars), Orca Run Replay (iflytek/skillhub, 5.2k stars), PicoClaw Agent (sipeed/picoclaw, 30k stars) and Chatgpt Apps (Haohao-end/openagent, 807 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ix?

ix-infrastructure (a GitHub organization) maintains it in ix-infrastructure/Ix, which has 1,030 GitHub stars. The repository was last updated on October 7, 2026.

Source: ix-infrastructure/Ix on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.