adcm-agent: Instructions file for Claude Code

AGENTS.md

adcm-agent AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from arenadata/adcm-agent. It costs 1,902 tokens per session, scanned A, original, Apache-2.0.

A set of repository rules for writing ADCM coding-agent skills, commands, agents, and scripts.

In plain words
What is it for?
Use it when adding or editing ADCM add-ons, including their directory layout, naming, metadata, documentation, and validation requirements.
Why use it?
It keeps contributions consistent and helps validation tools catch structural or formatting mistakes before they are submitted.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: ${CLAUDE_PLUGIN_ROOT} variable, but also the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions subagents.

This is arenadata/adcm-agent's own configuration. It tells Claude Code, Codex and OpenCode how to work on adcm-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything adcm-agent configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to arenadata/adcm-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/arenadata/adcm-agent/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/arenadata/adcm-agent

Made for: Claude Code, Codex, OpenCode.

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 adcm-agent AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arenadata/adcm-agent/agents-md/github.svg)](https://agentmods.dev/instructions/arenadata/adcm-agent/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/arenadata/adcm-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/arenadata/adcm-agent/agents-md/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 adcm-agent AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/arenadata/adcm-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/arenadata/adcm-agent/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,902 This file is loaded in full into every session.
When invoked 1,902 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01902 $0.01902
Opus 5.5 $0.00761 $0.00761
Sonnet 5.5 $0.00380 $0.00380
Haiku 4.5 $0.00190 $0.00190

Measured 2mo ago against content hash 57d03c388874, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adcm-agent AGENTS.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 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.

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.

AGENTS.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoring contract

How skills, commands, agents and scripts in this repository are written. Read this before adding or editing one. tools/validate_skills.py and tools/check_scripts.py enforce the mechanical half; the rest is style you are expected to match by hand.

Repository layout

.claude-plugin/
  plugin.json          # every skill directory must be listed in skills[]
  marketplace.json     # one plugin entry, source "./"
skills/<skill-name>/
  SKILL.md             # required
  reference/*.md       # optional: lookup material (tables, inventories, key lists)
commands/*.md          # slash commands
agents/*.md            # subagents
scripts/               # what the skills actually run - shipped to users
tools/                 # this repository's own validation - not shipped as behaviour

Skill directories are kebab-case and always prefixed adcm-. SKILL.md is always uppercase. Commands are prefixed adcm- too, so they read as /adcm-build.

The rule this repository exists to enforce

No file here may contain a real ADCM instance address, account, credential or host name. Not in a skill, not in a command, not in a script default, not in a docstring, not in an example.

This is not a style preference. The skills this plugin replaces defaulted to one development stand's IP address and to admin/admin, which made them wrong for every other installation and put a credential in three git repositories. Everything instance-specific resolves at run time through scripts/adcm_env.py.

Both validators check this, and they check prose as well as code:

  • a literal IPv4 address that is not loopback or an RFC 5737 documentation range
  • an os.environ.get("ADCM_*", "<fallback>") with a baked-in default
  • a default account pair used as a value
  • a credential-looking assignment whose value is not a placeholder or an env var name

Write <ask the user>, $ADCM_URL, MY_VAR, adcm.example.internal instead.

Frontmatter

---
name: adcm-<topic>               # must equal the directory name
description: <what it does> - <inventory of the concepts it covers>. Use when <trigger>, <trigger>, or <symptom>.
license: Apache-2.0
metadata:
  author: Arenadata
  version: "0.1.0"
  adcmVersion: "2.x (API v2)"
---

Read the full file on GitHub · 160 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 First seen · 160 lines · 1,902 tokens per session scan A 57d03c388874

Subscribe to this mod's changes

adcm-agent AGENTS.md is an instructions file published in the GitHub repository arenadata/adcm-agent (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,902 tokens to every session, about $0.0076 per session on Opus 5.5. 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.

Related

adcm-agent AGENTS.md compared with instructions from other repositories

adcm-agent AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
adcm-agent AGENTS.mdarenadata/adcm-agentInstructions file22mo agoApache-2.0A1,902Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot