agentmods.dev

init

init is a skill for Claude Code from XBlueSky/cc-loadout. It costs 128 tokens per session (1,369 once invoked), scanned B, original, MIT.

A guided setup tool for cc-loadout, a command-line utility that chooses which Claude Code plugins are active in each code repository.

In plain words
What is it for?
It helps inspect installed plugins, create repository-specific profiles, and activate the right plugins for each repository.
Why use it?
It avoids manually editing configuration files and helps ensure the selected plugin setup is actually applied.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions Claude Code.

Part of the cc-loadout plugin — 4 skills, 2 hooks shipped together

not rated 2repo changed 2mo ago B scan 128 tokens original MIT

Good fit It helps inspect installed plugins, create repository-specific profiles, and activate the right plugins for each repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xbluesky/cc-loadout/init
View source ↗ XBlueSky/cc-loadout cc-loadout.pages.dev
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.

Any agent
npx skills add XBlueSky/cc-loadout --skill init
Clone the repo
git clone --depth 1 https://github.com/XBlueSky/cc-loadout

Made for: Claude Code.

Or install cc-loadout, the plugin that ships this one along with the rest of its 4 skills, 2 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 init

README.md
[![agentmods](https://agentmods.dev/badge/skills/xbluesky/cc-loadout/init/github.svg)](https://agentmods.dev/skills/xbluesky/cc-loadout/init)
Your own site
<a href="https://agentmods.dev/skills/xbluesky/cc-loadout/init"><img src="https://agentmods.dev/badge/skills/xbluesky/cc-loadout/init/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.

agentmods 80×15 button for init

Your own site · 80×15
<a href="https://agentmods.dev/skills/xbluesky/cc-loadout/init"><img src="https://agentmods.dev/badge/skills/xbluesky/cc-loadout/init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,369 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00128 $0.01369
Opus 5.5 $0.00051 $0.00548
Sonnet 5.5 $0.00026 $0.00274
Haiku 4.5 $0.00013 $0.00137

Measured 2mo ago against content hash 107611c79391, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

init 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 2mo 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.

**global** enabled set in `~/.claude/settings.json` (universal stays on; every other
skills/init/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guided cc-loadout profile creation

You help the user build and activate ~/.claude/profiles/profiles.json for cc-loadout — the config that decides which Claude Code plugins load in which repos. You drive the cc-loadout CLI; you do not hand-write the JSON or touch settings.json yourself — the CLI validates and writes everything.

The end state (the "loadout" model): universal plugins stay enabled globally, every other managed plugin is turned off globally, and each repo re-enables just the plugins of the profiles it matches. That takes two CLI calls — profile init --assign (writes the config + adjusts the global set) and profile apply --all (enables per repo). Do both, or the change does not take effect.

Prerequisite

The cc-loadout CLI must be installed (cc-loadout --version). If it's missing, that's normally the SessionStart hook not having run yet or having failed — have the user start a fresh session first; install.sh (see the cc-loadout README) is the fix only for someone using the CLI without the plugin.

Steps

  1. Inspect. Find out where the user keeps their git repos; ask for an absolute path if you don't already know it (cc-loadout does NOT expand ~ — use a full path). Then:

    cc-loadout profile inventory --json --root <that path>

    (Drop --root to use their existing scan_roots.) You get back { "schema_version": 1, "plugins": [...], "repos": [...], "suggested_profiles": [...] }. Ignore schema_version and any unknown key. Read plugins[].key, repos, and suggested_profiles[] (each suggested profile has a name and the detect markers found in that cluster of repos).

  2. Interview. Using the inventory, decide the assignment with the user:

    • Which installed plugins are universal (loaded in every repo)? Good universal picks never mis-fire anywhere (e.g. search / code-review tools).
    • For each entry in suggested_profiles, which of the remaining plugins should it add? Confirm or skip each suggestion. (Profile names come from suggested_profiles[].name — you cannot invent new profile names here; the detect rules are derived from the scan.)

Read the full file on GitHub · 107 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. 2mo ago Changed · -1 lines 107611c79391
  2. 2mo ago First seen · 108 lines · 128 tokens per session scan B 24598586ce3b

Subscribe to this mod's changes

init is a skill published in the GitHub repository XBlueSky/cc-loadout (2 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 1,369 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.

Building agents
Related

init compared with skills from other repositories

init next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
initXBlueSky/cc-loadoutSkill21mo agoMITB128Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code