What is agentic-monorepo-template CLAUDE.md?

Repository instructions for an agent-focused monorepo. A monorepo is one repository containing multiple related parts of a project, and these instructions define its layout, conventions, backlog, and commands.

Use it when agents plan, implement, or review features in this template and need to follow its command contract and pipeline.

It gives agents a shared process for checking, testing, building, running, and smoke-testing the project. Smoke tests exercise important user journeys in the running application, not just whether it starts.

How chrille0313/agentic-monorepo-template configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to chrille0313/agentic-monorepo-template. 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/chrille0313/agentic-monorepo-template/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/chrille0313/agentic-monorepo-template

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/chrille0313/agentic-monorepo-template/claude-md/github.svg)](https://agentmods.dev/instructions/chrille0313/agentic-monorepo-template/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/chrille0313/agentic-monorepo-template/claude-md"><img src="https://agentmods.dev/badge/instructions/chrille0313/agentic-monorepo-template/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/chrille0313/agentic-monorepo-template/claude-md"><img src="https://agentmods.dev/badge/instructions/chrille0313/agentic-monorepo-template/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 917 This file is loaded in full into every session.

When invoked 917 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.

Model	Per session	Once invoked
Fable 5.1	$0.00917	$0.00917
Opus 5.5	$0.00367	$0.00367
Sonnet 5.5	$0.00183	$0.00183
Haiku 4.5	$0.00092	$0.00092

Measured yesterday against content hash d71b42441336, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentic-monorepo-template 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 yesterday.

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 · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Monorepo Template

This repo is agentic-first: features flow through a PM -> implementer -> reviewer pipeline (see README). These instructions are shared by every agent in that pipeline.

Command contract

Check (lint + typecheck): TODO: run /setup-stack
Test: TODO: run /setup-stack
Build: TODO: run /setup-stack
Run (start the app so an agent can exercise it, via a stable port/URL or CLI entrypoint): TODO: run /setup-stack
Smoke (drive the running app through its critical user journeys; deterministic, seeded): TODO: run /setup-stack

Check, test, and build are hard gates: they must exit 0 before agent review means anything. Review layers on top of deterministic checks, never replaces them, and one runner owns each gate rather than every agent repeating it. Run and smoke exist so agents can verify behavior, not just code: this repo treats "an agent can start and exercise the app" as a first-class requirement of the stack. Smoke is a living suite that every feature adding a user journey extends; a command that still only proves the process boots has stopped earning its runtime. The full suite gates the PR in CI.

If a contract command is still TODO, say so and stop. Do not invent a substitute.

Layout

This is a monorepo with a fixed structure, independent of stack and tooling:

apps/<name>: deployable applications. Every deployable lives here, even when there is only one.
packages/<name>: shared libraries used by apps.
Group feature code by domain (vertical slices), not by technology.

Backlog

If the repo has a GitHub remote, GitHub Issues are the backlog. Use gh issue list/view.
Otherwise, BACKLOG.md is the backlog.
A task is ready when it has a spec: goal, acceptance criteria, out-of-scope, verification plan.
Dependencies: label the dependent issue blocked and write "Blocked by #N" in its body. The PM removes the label once every blocker is closed.
The in-progress label marks a task actively being worked; /build sets and clears it.
A GitHub Project board, when configured, mirrors issue state for humans (.github/workflows/board-sync.yml). Issues stay the source of truth; agents never read or update the board.

Read the full file on GitHub · 54 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.

yesterday First seen · 54 lines · 917 tokens per session scan A d71b42441336

Subscribe to this mod's changes

agentic-monorepo-template CLAUDE.md is an instructions file published in the GitHub repository chrille0313/agentic-monorepo-template (6 stars, last pushed 1mo ago), licensed MIT. It adds 917 tokens to every session, about $0.0037 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 2026-11-07.

Project management Testing agent-loop agentic-loop agentic-workflow ai-agents anthropic automation

agentic-monorepo-template CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentic-monorepo-template CLAUDE.mdchrille0313/agentic-monorepo-template	Instructions file	6	1mo ago	MIT	A	917	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

agentic-monorepo-template: Instructions file for Claude Code