What is ix-claude-plugin CLAUDE.md?

Repository instructions for ix-claude-plugin, a Claude Code plugin that connects an AI assistant to Ix Memory, a structured system for storing and using project knowledge. They describe the plugin's mental model, files, skills, agents, and development rules.

Use them when adding or updating skills, agents, hook scripts, tests, or marketplace information in ix-claude-plugin. They also explain which Ix commands to use while navigating the codebase.

They help contributors understand how the plugin is organized and how its memory, hooks, and reasoning tools fit together. This reduces guesswork when changing the repository.

How ix-infrastructure/ix-claude-plugin configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ix-infrastructure/ix-claude-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ix-infrastructure/ix-claude-plugin/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ix-infrastructure/ix-claude-plugin

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ix-infrastructure/ix-claude-plugin/claude-md/github.svg)](https://agentmods.dev/instructions/ix-infrastructure/ix-claude-plugin/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ix-infrastructure/ix-claude-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/ix-infrastructure/ix-claude-plugin/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ix-infrastructure/ix-claude-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/ix-infrastructure/ix-claude-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,883 This file is loaded in full into every session.

When invoked 1,883 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01883	$0.01883
Opus 5.5	$0.00753	$0.00753
Sonnet 5.5	$0.00377	$0.00377
Haiku 4.5	$0.00188	$0.00188

Measured today against content hash 4f8552ed50ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ix-claude-plugin CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ix-claude-plugin

For the canonical Ix operating model (command taxonomy, routing, fallback behavior), see skills/shared.md. This file covers contributing to ix-claude-plugin specifically.

This repo is the Claude Code plugin for Ix Memory. When working in this repo, use ix commands to navigate it just like any other codebase. This repo contains shipped skills, hook scripts, tests, and marketplace metadata.

Cognitive Model

Claude + Ix operates as a three-layer system:

Ix Graph        = structured memory
Claude          = reasoning engine
Skills / Agents = task abstractions over the graph

The plugin exists to make that model usable inside Claude Code through install-time teaching, hook-driven context injection, and higher-level reasoning skills.

Repo Structure

skills/
  shared.md                  canonical install-time Ix model
  ix-help/                   router skill
  ix-understand/             architecture mental model
  ix-investigate/            symbol deep dive
  ix-impact/                 pre-edit blast radius
  ix-plan/                   risk-ordered change planning
  ix-debug/                  bug investigation
  ix-architecture/           design health audit
  ix-docs/                   narrative-first documentation
  */*-brief.md               role briefs a skill hands to ix-explorer
agents/
  ix-explorer.md             the one agent
hooks/
  hooks.json                 active Claude Code hook registry
  ix-briefing.sh             prompt-time session context
  ix-annotate.sh             visible attribution / briefing annotation
  ix-intercept.sh            Grep / Glob interception (off unless IX_GREP_INTERCEPT=on)
  ix-bash.sh                 grep / rg detection inside Bash commands (off unless IX_GREP_INTERCEPT=on)
  ix-pre-edit.sh             pre-edit impact warning (off unless IX_PRE_EDIT_GATE=on)
  ix-ingest.sh               post-edit guarded root-map request
  ix-dependents.sh           post-edit dependents of the changed symbols (ix hook; off unless IX_EDIT_DEPENDENTS=on)
  ix-map.sh                  async Stop-time guarded root-map request
  ix-read.sh                 disabled placeholder; not registered
  ix-lib.sh, ix-errors.sh, ix-ledger.sh, ix-report.sh, lib/index.sh
  lib/timing.sh              IX_DEBUG_LOG EXIT line; lib/bash-write.sh: can a Bash line write?
tests/
  test_hooks.sh              integration harness
  test_real_ix.sh            hooks against a real, released ix (CI job real-ix)
  bench_hooks.sh             median ms per hook on a representative payload
  mock-ix.sh                 ix CLI stub
  fixtures/                  hook inputs and expected outputs
.claude-plugin/
  plugin.json                plugin manifest
  marketplace.json           marketplace metadata

Active hooks are defined by hooks/hooks.json: briefing + annotate on prompt submit, intercept for Grep|Glob, bash interception for Bash, pre-edit warnings for edits, ingest on post-edit, and full map refresh on Stop.

Read the full file on GitHub · 159 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed · +15 lines · +292 tokens per session 4f8552ed50ca
19d ago Changed · +2 lines · +76 tokens per session 48f202c442f3
20d ago Changed · +7 lines · +141 tokens per session d11a85d9872e
1mo ago Changed · +1 lines · +19 tokens per session 973a61d2917e
1mo ago Changed · +2 lines · +63 tokens per session fb87934c9df3
1mo ago Changed · +2 tokens per session 7711fb1f82e2
2mo ago First seen · 132 lines · 1,290 tokens per session scan A 6d35ae6175f5

Subscribe to this mod's changes

ix-claude-plugin CLAUDE.md is an instructions file published in the GitHub repository ix-infrastructure/ix-claude-plugin (7 stars, last pushed today), licensed Apache-2.0. It adds 1,883 tokens to every session, about $0.0075 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ix-claude-plugin CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ix-claude-plugin CLAUDE.mdix-infrastructure/ix-claude-plugin	Instructions file	7	today	Apache-2.0	A	1,883	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	today	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

ix-claude-plugin: Instructions file for Claude Code