claude-start: Instructions file for Claude Code

CLAUDE.md

claude-start CLAUDE.md is an instructions file for Claude Code from moneytosms/claude-start. It costs 749 tokens per session, scanned A, original, MIT.

A project instruction file that tells the coding agent about the project's technology, required checks, tools, context limits, and error-handling rules. It also requires a short canary marker after each completed task.

In plain words
What is it for?
Use it to record the project's stack and commands, require verification markers, define when to save progress, and specify how to handle minor and major errors.
Why use it?
It gives the agent project-specific working rules instead of leaving those decisions implicit. The canary marker helps indicate whether the task context was retained.

Instructions file for Claude Code

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

This is moneytosms/claude-start's own configuration. It tells Claude Code how to work on claude-start 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 claude-start configures →

Reuse

Borrowing it

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

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 claude-start CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/moneytosms/claude-start/claude-md"><img src="https://agentmods.dev/badge/instructions/moneytosms/claude-start/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 749 This file is loaded in full into every session.
When invoked 749 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 $0.00749 $0.00749
Opus 5 $0.00375 $0.00375
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 9d ago against content hash d76d1044d840, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-start 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 9d 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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[PROJECT_NAME]

[One sentence: what this project does.]

Stack

  • Runtime:
  • Framework:
  • Key deps:
  • Test:
  • Lint:
  • Format:
  • Build:
  • Deploy:
  • RTK wrappers:

Canary

Every completed task must end with: [Canary:PROJECT_NAME:TASK_NAME] Can't produce it = context dropped. Stop and say so.

Tooling

  • RTK — Bash output auto-compressed. First layer for ALL matching commands, raw only if no wrapper exists. See RTK wrappers in Stack above for this project's exact commands. Full list: rtk help.
  • ctx7npx ctx7 library <name> <query> before touching any external API. Never rely on training data for library APIs.
  • Caveman/caveman for long sessions. /caveman off to disable.
  • Handoff — use /handoff before ending a session, not /compact.

Context rules

  • Flag before any phase that risks one context window.
  • Running low → /checkpoint, then stop. SessionStart hook will surface it.
  • All commands must work headless.

Error protocol

  • Minor (typo, wrong flag): note inline, continue.
  • Major (wrong architecture, repeated mistake):
    1. Append to .claude/errors.md
    2. If pattern → create .claude/skills/<name>.md
    3. If approach changes → append to Learned rules below

Agent output conventions

Anything we build that talks back to Claude (hooks, agent defs, skills, subagent reports) follows .claude/rules/agent-output-conventions.md: no silent truncation, explicit empty states, end with a concrete next command.

Read the full file on GitHub · 67 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. 9d ago First seen · 67 lines · 749 tokens per session scan A d76d1044d840

Subscribe to this mod's changes

claude-start CLAUDE.md is an instructions file published in the GitHub repository moneytosms/claude-start (2 stars, last pushed 16d ago), licensed MIT. It adds 749 tokens to every session, about $0.0037 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 2026-08-31.

Related

Other instructions, from other repositories