dev-templates: Instructions file for Claude Code

CLAUDE.md

dev-templates CLAUDE.md is an instructions file for Claude Code from helpers-no/dev-templates. It costs 539 tokens per session, scanned C, original, MIT.

Repository instructions for dev-templates, a project that uses written plans to guide development work and requires commands to run inside a development container.

In plain words
What is it for?
Use them before changing dev-templates to find active plans, create an investigation or plan, wait for approval, update progress, and use the correct container and project guides.
Why use it?
They prevent unapproved implementation work and point agents to the project's workflow, plans, and setup documentation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is helpers-no/dev-templates's own configuration. It tells Claude Code how to work on dev-templates 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 dev-templates configures →

Reuse

Borrowing it

Nothing to install: this file belongs to helpers-no/dev-templates. 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/helpers-no/dev-templates/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/helpers-no/dev-templates

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 dev-templates CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/helpers-no/dev-templates/claude-md/github.svg)](https://agentmods.dev/instructions/helpers-no/dev-templates/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/helpers-no/dev-templates/claude-md"><img src="https://agentmods.dev/badge/instructions/helpers-no/dev-templates/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 dev-templates CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/helpers-no/dev-templates/claude-md"><img src="https://agentmods.dev/badge/instructions/helpers-no/dev-templates/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 539 This file is loaded in full into every session.
When invoked 539 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.00539 $0.00539
Opus 5.5 $0.00216 $0.00216
Sonnet 5.5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured 1mo ago against content hash 799e33f9ef56, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

dev-templates CLAUDE.md scanned grade C with 1 finding 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 1mo 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

(`~/.local/bin/urb`) are host commands and are not covered by that rule. Do not refuse fleet work
CLAUDE.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Templates

How We Work

ALL work follows the plan-based workflow. Before writing any code:

  1. Check website/docs/ai-developer/plans/active/ for in-progress work
  2. Create an INVESTIGATE-.md or PLAN-.md in website/docs/ai-developer/plans/backlog/
  3. Wait for user approval before implementing
  4. Update the active plan file as you work — mark each task [x] immediately after completing it, mark phase headings as DONE
  5. Read website/docs/ai-developer/WORKFLOW.md for the full process
  6. Read website/docs/ai-developer/PLANS.md for plan structure

Where commands run. Project commands — package managers, builds, tests, tooling — run inside the devcontainer; see DEVCONTAINER.md. Your own agent session runs on the host, in tmux: reading files, git, and the bus client (~/.local/bin/urb) are host commands and are not covered by that rule. Do not refuse fleet work because of it.

Fleet coordination

You are dev-templates, an agent on the URB fleet. Fleet work does not arrive in this repo.

  • Your inbox is a query, not a directory: ~/.local/bin/urb inbox --id dev-templates (open issues labelled to:dev-templates in terchris/urb-agents).
  • The protocol is protocol/communication.md in terchris/urb-agents, read remotely. Do not clone that repository and do not copy protocol/ here.
  • See COORDINATION.md for where gh applies and where urb does.
  • There is no file bus. The bus is GitHub issues; talk/ and mailboxes/ directories are not read by anything. Do not create one.

Project Details

Read website/docs/ai-developer/README.md for the complete AI developer guide.

Read website/docs/ai-developer/project-dev-templates.md for project-specific setup, tools, and commands.

Read the full file on GitHub · 38 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. 1mo ago Changed · +17 lines · +281 tokens per session scan A → C 799e33f9ef56
  2. 2mo ago First seen · 21 lines · 258 tokens per session scan A 3d9ce4079c61

Subscribe to this mod's changes

dev-templates CLAUDE.md is an instructions file published in the GitHub repository helpers-no/dev-templates (2 stars, last pushed today), licensed MIT. It adds 539 tokens to every session, about $0.0022 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

dev-templates CLAUDE.md compared with instructions from other repositories

dev-templates CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dev-templates CLAUDE.mdhelpers-no/dev-templatesInstructions file2todayMITC539Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
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