agentmods.dev

apexyard: Instructions file for Claude Code

CLAUDE.md

apexyard CLAUDE.md is an instructions file for Claude Code from me2resh/apexyard. It costs 5,477 tokens per session, scanned A, original, MIT.

A set of instructions for running apexyard, a system for managing multiple software projects with Claude Code. It describes setup, project records, team roles, shared memory, and development processes.

In plain words
What is it for?
Use it when operating or extending an apexyard portfolio, following its development process, or working on one of its managed projects.
Why use it?
It gives the coding agent project-specific rules and context, reducing the need to explain how the repository and its projects are organised.

Instructions file for Claude Code

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

This is me2resh/apexyard's own configuration. It tells Claude Code how to work on apexyard 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 apexyard configures →

not rated 542repo changed 15d ago A scan 5,477 tokens original MIT
View source ↗ me2resh/apexyard apexyard.ai
Reuse

Borrowing it

Nothing to install: this file belongs to me2resh/apexyard. 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/me2resh/apexyard/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/me2resh/apexyard

Made for: Claude Code.

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 apexyard CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/me2resh/apexyard/claude-md/github.svg)](https://agentmods.dev/instructions/me2resh/apexyard/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/me2resh/apexyard/claude-md"><img src="https://agentmods.dev/badge/instructions/me2resh/apexyard/claude-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 apexyard CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/me2resh/apexyard/claude-md"><img src="https://agentmods.dev/badge/instructions/me2resh/apexyard/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,477 This file is loaded in full into every session.
When invoked 5,477 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 $0.05477 $0.05477
Opus 5.5 $0.02191 $0.02191
Sonnet 5.5 $0.01095 $0.01095
Haiku 4.5 $0.00548 $0.00548

Measured 15d ago against content hash 75c76b792170, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

apexyard 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 15d 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 · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ApexYard -- A Multi-Project Forge for Claude Code

You are the Chief of Staff running a portfolio of projects inside apexyard. You don't add apexyard to a project — projects get forged inside it. Your job: ensure every project ships production-ready MVPs under a strict SDLC, with shared memory across the portfolio so projects learn from each other's experience. Processes are followed, quality is maintained, and work moves efficiently from idea to production.

Load a named file under .claude/rules/ when the work matches that rule. Do not load every rule at session start. /setup and SessionStart write this clone's absolute rule-directory exclude into the gitignored .claude/settings.local.json. Personal and managed-project rules remain eligible to load. Existing user exclusions still apply. A newly written or repaired exclude takes effect in the next session. Mechanical gates live in .claude/hooks/*.sh. See AgDR-0160 and AgDR-0233.

SETUP

  1. Read onboarding.yaml for company-specific configuration. Resolve the path via the portfolio paths helper so split-portfolio v2 adopters read the sibling repo's copy instead of the (template-default) one in the fork:

    source "$(git rev-parse --show-toplevel)/.claude/hooks/_lib-portfolio-paths.sh"
onboarding=$(portfolio_onboarding_path)
# Read "$onboarding" with the Read tool

    In single-fork mode this still resolves to <ops-root>/onboarding.yaml — same file you'd reach without the helper. The indirection only matters in split-portfolio mode but costs nothing to apply unconditionally.

  2. Read apexyard.projects.yaml — the portfolio registry listing every repo under management

  3. Understand the team structure and roles

  4. Apply the workflows and standards defined in this stack

PORTFOLIO MODEL

ApexYard governs a portfolio of repos as one organisation. The repo this CLAUDE.md lives in is your ops repo — a fork of me2resh/apexyard cloned into your organisation (optionally renamed to your-org/ops or similar). The registry file apexyard.projects.yaml at the ops-repo root lists every project under management. Per-project docs live in projects/<name>/; optional live working copies of each managed repo live in workspace/<name>/ (gitignored).

Read the full file on GitHub · 302 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. 15d ago Changed · +1 lines · +23 tokens per session 75c76b792170
  2. 22d ago Changed · +1 lines · -36 tokens per session 0ed53585f0b5
  3. 29d ago Changed · +1 lines · +22 tokens per session 5c04264feb8c
  4. 1mo ago Changed · +1 lines · +212 tokens per session 0b004ddbeda4
  5. 1mo ago Changed · +1 lines · +24 tokens per session d62108475762
  6. 1mo ago Changed · -41 lines · -2,237 tokens per session 0a6d364f9003
  7. 1mo ago Changed · +2 lines · +345 tokens per session 9f675b279918
  8. 2mo ago First seen · 336 lines · 7,124 tokens per session scan A 6d34318ad61e

Subscribe to this mod's changes

apexyard CLAUDE.md is an instructions file published in the GitHub repository me2resh/apexyard (542 stars, last pushed yesterday), licensed MIT. It adds 5,477 tokens to every session, about $0.0219 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 2026-09-03.

Building agentsClaude CodeProject managementagentic-codingai-agentsai-governanceclaude-code-hooksclaude-code-skills
Related

apexyard CLAUDE.md compared with instructions from other repositories

apexyard CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
apexyard CLAUDE.mdme2resh/apexyardInstructions file542yesterdayMITA5,477Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode