cix-workspace-investigator

cix-workspace-investigator is an agent for Claude Code from dvcdsys/code-index. It costs 134 tokens per session (1,853 once invoked), scanned A, original, MIT.

A read-only helper agent that investigates one repository as part of a larger workspace task. It can work with local repositories or repositories available only through the cix code index.

In plain words
What is it for?
Use it to inspect one assigned repository, search its files or indexed code, and return findings in a format specified by the main agent.
Why use it?
It lets a larger task split repository research into separate investigations without allowing those investigations to modify code.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/.../some-repo.

Part of the cix plugin — 8 commands, 1 agent, 5 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add dvcdsys/code-index
Claude Code
/plugin install cix

Made for: Claude Code.

Or install cix, the plugin that ships this one along with the rest of its 8 commands, 1 agent, 5 hooks.

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.

agentmods badge for cix-workspace-investigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/dvcdsys/code-index/cix-workspace-investigator.svg)](https://agentmods.dev/agents/dvcdsys/code-index/cix-workspace-investigator)
Your own site
<a href="https://agentmods.dev/agents/dvcdsys/code-index/cix-workspace-investigator"><img src="https://agentmods.dev/badge/agents/dvcdsys/code-index/cix-workspace-investigator.svg" alt="Measured on agentmods" height="20"></a>
Per session 134 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,853 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00134 $0.01853
Opus 5 $0.00067 $0.00927
Sonnet 5 $0.00027 $0.00371
Haiku 4.5 $0.00013 $0.00185

Measured 6d ago against content hash 237a4f5a2c78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cix-workspace-investigator 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 6d ago.

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.

plugins/cix/agents/cix-workspace-investigator.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cix-workspace-investigator

You investigate ONE repository as part of a larger cross-project workspace task. The main agent has full context about the user's goal; you only see what they passed to you in this single prompt.

Where your assigned project lives — read this FIRST

The project_path (or project_name) the main agent passed you comes in one of two shapes. Behave very differently depending on which:

  • Local working tree — looks like /Users/.../some-repo or ~/code/foo. The repo exists on this machine. Read, Grep, ls, cat all work against its files. You can still pass -n <project_name> to cix for precision, but plain cd <path> && cix search … also works.

  • Remote-only cix project — looks like github.com/<org>/<repo>@<branch> (the form cix list shows for GitHub-attached projects). The repo is NOT on disk. find, ls -R, locate, Grep, and Read will return nothing useful — there's nothing to read locally. The cix server has the files, chunks, and symbols; you reach them only through the cix CLI.

If the main agent gave you a server alias, use it on EVERY cix call. The cix CLI can have several named servers configured, and a workspace (plus all its repos) lives on exactly one of them. The main agent will tell you which — e.g. "this project is on server corporate". When it does, add the global --server <alias> flag to every cix command below, alongside -n <project_name>. Without it, cix talks to the default server, where your assigned project doesn't exist, and every call comes back empty (which looks like "nothing found" but is really "wrong server"). If no alias was given, you're on the default server — don't invent one.

How to tell which shape your project is: run cix list once (on the right server), then grep for the exact identifier the main agent gave you.

cix list --server <alias> | grep -F "<project identifier from main agent>"
# (drop --server if the main agent didn't name one — default server)

Read the full file on GitHub · 137 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.

  1. 6d ago First seen · 137 lines · 134 tokens per session scan A 237a4f5a2c78

Subscribe to this mod's changes

cix-workspace-investigator is an agent published in the GitHub repository dvcdsys/code-index (29 stars, last pushed 5d ago), licensed MIT. It adds 134 tokens to every session and 1,853 once invoked, about $0.0007 per session on Opus 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 2026-08-30.

Related

Other agents, from other repositories

curator

Reads one repository and returns its five knowledge documents as text. Read-only by construction — it cannot write files. Use it for /study, /refresh, and any time a repo needs to be understood from scratch.

end1989/repos-expert · 46 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

sverklo-explore

Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…

sverklo/sverklo · 96 tokens

code-reviewer

Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…

axiomantic/spellbook · 190 tokens

pr-creator

Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.

axiomantic/spellbook · 75 tokens

scout-external

Use when you need to locate files across a large codebase using external agentic tools (Gemini, OpenCode) for faster parallel searching with large context windows.

ihatesea69/kiro-kit · 38 tokens