agentmods.dev

adrkit CLAUDE.md

Claude Code instructions for the adrkit repository, whose shared project guidance is stored in AGENTS.md. They explain how Claude Code loads that guidance and how to validate or install adrkit as a Claude Code plugin.

In plain words
What is it for?
Use them when Claude Code is working in adrkit, especially before making changes, installing the local plugin, or validating its plugin manifest.
Why use it?
They prevent duplicated and drifting instructions while giving Claude Code the repository rules and the commands needed to work with its plugin.

Instructions file

11 2d ago A scan 263 tokens original Apache-2.0
View the source file mbeacom/adrkit
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/mbeacom/adrkit/claude-md
Clone the repo
git clone --depth 1 https://github.com/mbeacom/adrkit
Per session 263 This file is loaded in full into every session.
When invoked 263 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 $0.00263 $0.00263
Opus 5 $0.00131 $0.00131
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00026 $0.00026

Measured 2d ago against content hash be4569a51737, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adrkit 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 · 26 lines

What it actually says

adrkit — Claude Code

Project memory for this repository is host-neutral and lives in one file.

@AGENTS.md

Read AGENTS.md before doing anything else. It carries the project overview, the surfaces and their current evidence-ladder status, the Bun toolchain rules, and the agent working-directory rules — including the two that have been violated in practice, about never writing to the maintainer's main checkout and never deleting a branch on commit ancestry alone.

Nothing project-specific is duplicated here on purpose. A second copy costs context on every session and drifts from the first.

Claude Code specifics

  • The @AGENTS.md line above is a Claude Code import, so the shared memory is loaded even when only this file is read.
  • This repository is also its own plugin marketplace. To work with the plugin it ships, /plugin marketplace add mbeacom/adrkit then /plugin install adrkit@adrkit. Validate local changes to it with claude plugin validate packages/adapters/agent-plugin — that validator is stricter than GitHub Copilot CLI's loader and is how the manifest's shape was settled (see ADR-0028).
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 · 26 lines · 263 tokens per session scan A be4569a51737

Subscribe to this mod's changes

adrkit CLAUDE.md is an instructions file published in the GitHub repository mbeacom/adrkit (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 263 tokens to every session, about $0.0013 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.

Planningadrai-agentsarchitecturearchitecture-decision-recordsbackstagedeveloper-experience
Related

Other instructions, from other repositories

cli CLAUDE.md

Instructions for archgate/cli, covering claude.md, technology stack, commands, validation gate and git hooks (git 2.54+).

archgate/cli · 2,551 tokens

mcp-adr-analysis-server copilot-instructions.md

Instructions for tosin2013/mcp-adr-analysis-server, covering mcp adr analysis server - ai coding agent instructions, project overview, critical technical conventions, esm-only module system and typescript configuration.

tosin2013/mcp-adr-analysis-server · 2,839 tokens

codebase-intel CLAUDE.md

Instructions for MutharasuArchunan13/codebase-intel, covering codebase intel — project claude.md, project overview, tech stack, architecture and module responsibilities.

MutharasuArchunan13/codebase-intel · 1,248 tokens

adr copilot-instructions.md

Instructions for zircote-plugins/adr, covering copilot instructions, project overview, key components, plugin structure and development guidelines.

zircote-plugins/adr · 256 tokens

adr-kit CLAUDE.md

Instructions for rvdbreemen/adr-kit, covering adr kit, backlog.md, werken in deze repo and graphify.

rvdbreemen/adr-kit · 797 tokens

docflow AGENTS.md

Instructions for EvolveHQ/docflow, covering agents.md, what this repository is, repository structure, hard rules when editing adrs and domain-specific hard rules.

EvolveHQ/docflow · 1,680 tokens