claude-code-starter-kit CLAUDE.md

claude-code-starter-kit CLAUDE.md is an instructions file for coding agents from muratsilahtaroglu/claude-code-starter-kit. It costs 1,006 tokens per session, scanned A, original, MIT.

A project constitution and session guide for Claude Code, an AI coding assistant. It tells the assistant which project rules, handover notes, lessons, and tasks to load and how to resume work.

In plain words
What is it for?
Use it to organize project rules, handovers, lessons, task lists, architecture decisions, testing expectations, and change records.
Why use it?
It keeps coding sessions consistent and helps the assistant continue unfinished work without overlooking project decisions or required checks.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/muratsilahtaroglu/claude-code-starter-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/muratsilahtaroglu/claude-code-starter-kit

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-code-starter-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/muratsilahtaroglu/claude-code-starter-kit/claude-md.svg)](https://agentmods.dev/instructions/muratsilahtaroglu/claude-code-starter-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/muratsilahtaroglu/claude-code-starter-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/muratsilahtaroglu/claude-code-starter-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,006 This file is loaded in full into every session.
When invoked 1,006 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01006 $0.01006
Opus 5 $0.00503 $0.00503
Sonnet 5 $0.00201 $0.00201
Haiku 4.5 $0.00101 $0.00101

Measured 4d ago against content hash d61f81e00a72, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-starter-kit 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 4d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — project constitution (TEMPLATE)

Claude Code reads this first every session. The four @-imports below auto-load the working rules, the running handover, the lessons database, and the task board — always in context, re-injected from disk after every compaction. Keep this file lean (< ~200 lines); push sometimes-relevant knowledge into .claude/skills/ and deterministic checks into .claude/hooks/. Fill in the <...> blanks.

@rules.md @HANDOVER.md @LESSONS.md @TASKS.md

Session protocol (rules.md §9)

  • Start: run /keel-continue (cross-checks the loaded memory against PLAN.md + git, then RESUMES half-done work, TAKES the lane's next assigned item via the comprehension gate, or reports IDLE) — or by hand: read the TOP block of HANDOVER.md + LESSONS.md + TASKS.md ## Now + recent git log; pick ONE ## Now item; verify tests pass before new work.
  • During: the moment a rule / must-run test / gotcha / failed approach is agreed or discovered — ask "shall I note this?" and append it to LESSONS.md immediately (don't wait for compaction).
  • End (or before compact): /keel-handover (new HANDOVER block) · delete done TASKS items · commit with approval. If any memory file exceeds its cap → /keel-distill. About to compact manually? Run /keel-compact — it bundles all of the above, verifies freshness, then hands off to /compact.
  • When compacting, always preserve: the list of modified files, open TASKS.md ## Now items, test commands, and any agreement not yet written to LESSONS.md (write it there first).

What we're building

<Purpose of the project in 2-3 sentences. What problem it solves, who uses it.>

Architecture (summary)

<Components and how they talk to each other. E.g.: API (FastAPI) + Worker + DB + Vector DB + LLM. A text diagram.>

Key decisions (ADRs in docs/adr/)

  • <ADR-0001: ...>
  • <ADR-0002: ...> (Every significant technical decision becomes an ADR; copy docs/adr/0000-adr-template.md.)

Read the full file on GitHub · 66 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. 4d ago First seen · 66 lines · 1,006 tokens per session scan A d61f81e00a72

Subscribe to this mod's changes

claude-code-starter-kit CLAUDE.md is an instructions file published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed today), licensed MIT. It adds 1,006 tokens to every session, about $0.0050 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.