agent-toolkit CLAUDE.md

Claude Code-specific contribution instructions for DiUS's agent-toolkit repository. Claude Code is Anthropic's coding assistant, and these rules explain the plugin files, subagents, commands, and local testing process.

In plain words
What is it for?
Updating plugin manifests, registering subagents or slash commands, validating changes, and testing the plugin from the working tree.
Why use it?
They tell contributors how this repository is packaged as a Claude Code plugin and how to keep its manifests, fallback behavior, and validation checks correct.

Instructions file

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 instructions/dius/agent-toolkit/claude-md
Clone the repo
git clone --depth 1 https://github.com/DiUS/agent-toolkit
Per session 430 This file is loaded in full into every session.
When invoked 430 The same file — it is already loaded in full.
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 $0.00430 $0.00430
Opus 5 $0.00215 $0.00215
Sonnet 5 $0.00086 $0.00086
Haiku 4.5 $0.00043 $0.00043

Measured 2d ago against content hash 8a38e26e4a2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-toolkit 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 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.

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 · 45 lines

What it actually says

CLAUDE.md

Guidance for Claude Code when working on this repository. Everything in AGENTS.md applies, so start there for the repo map, principles, and how to add each component type. This file only adds what's specific to Claude Code.

@AGENTS.md

Claude Code specifics

This repo is also a Claude Code plugin (single bundled plugin, agent-toolkit), which is the primary target.

  • Plugin manifests live in .claude-plugin/plugin.json (registers ./skills, ./commands, and each bundled agent) and marketplace.json (marketplace dius-agent-toolkit, plugin agent-toolkit, sourced from GitHub DiUS/agent-toolkit). Keep both valid JSON; scripts/validate.js checks them.
  • Subagents in agents/ are Claude Code workers a skill can delegate to (for example, to keep the main context lean or to run an isolated pass). Each is registered in the agents array of plugin.json. On non-Claude hosts they're absent, and the skill falls back to a generic sub-agent or inline work. Keep that fallback path intact when editing skill behaviour.
  • Commands in commands/ register as slash commands automatically via the plugin. They're a Claude Code convention; other agents fall back to reading the referenced skill directly.
  • Hooks are opt-in. Nothing under hooks/ is wired into plugin.json. Don't make a hook a dependency of any skill, command or agent in this repo.

Testing changes locally

# load the plugin from this working tree
claude --plugin-dir /path/to/agent-toolkit

# preview skill discovery for the npx-skills channel
npx skills add . --list

Before committing

Run the verification gate (also enforced in CI):

node scripts/validate.js
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 · 45 lines · 430 tokens per session scan A 8a38e26e4a2b

Subscribe to this mod's changes

agent-toolkit CLAUDE.md is an instructions file published in the GitHub repository DiUS/agent-toolkit (2 stars, last pushed 2d ago), licensed MIT. It adds 430 tokens to every session, about $0.0022 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 2026-08-31.