setup

A setup procedure for configuring Codachi as a Claude Code status line. A status line is the small display that shows information about the current coding session.

In plain words
What is it for?
Finding Codachi's built file, testing its command, updating Claude Code's settings, and telling the user to restart Claude Code.
Why use it?
It checks the existing configuration and preserves it while adding the command needed to display Codachi, warning if another status line is already configured.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/vincent-k2026/codachi/setup
Clone the repo
git clone --depth 1 https://github.com/vincent-k2026/codachi
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 225 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00008 $0.00225
Opus 5 $0.00004 $0.00112
Sonnet 5 $0.00002 $0.00045
Haiku 4.5 $0.00001 $0.00022

Measured 2d ago against content hash bbccaecdaf5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

setup scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

3. Read `~/.claude/settings.json` to check current statusline config
commands/setup.md · 32 lines

What it actually says

Codachi Setup

You are setting up codachi as the user's Claude Code statusline.

Steps

  1. Determine the absolute path to the dist/index.js file in this project
  2. Test that the command works by running: echo '{"model":{"display_name":"Test"},"context_window":{"used_percentage":50}}' | node <path>/dist/index.js
  3. Read ~/.claude/settings.json to check current statusline config
  4. Set the statusLine config:
{
  "statusLine": {
    "type": "command",
    "command": "node <absolute-path-to>/dist/index.js"
  }
}
  1. Tell the user to restart Claude Code for the pet to appear

Important

  • Use the absolute path to dist/index.js
  • Preserve any existing settings in settings.json
  • If there's already a statusLine configured, warn the user before overwriting
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. 2d ago First seen · 32 lines · 8 tokens per session scan B bbccaecdaf5a

Subscribe to this mod's changes

setup is a command published in the GitHub repository vincent-k2026/codachi (11 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 225 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.