What is agentsitter CLAUDE.md?

A set of instructions for analyzing configuration files that guide AI coding tools, such as CLAUDE.md or CODEX.md files. It describes checks for clarity, structure, missing information, duplication, and token use.

Use it to review, score, and improve configuration files for coding agents, and to produce an optimized version with categorized issues.

It helps keep agent instructions clear, complete, and efficient, while finding vague or repeated rules that may lead to inconsistent results.

How serdaraytac/agentsitter configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to serdaraytac/agentsitter. 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/serdaraytac/agentsitter/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/serdaraytac/agentsitter

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/serdaraytac/agentsitter/claude-md/github.svg)](https://agentmods.dev/instructions/serdaraytac/agentsitter/claude-md)

Your own site

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

Per session 532 This file is loaded in full into every session.

When invoked 532 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	$0.00532	$0.00532
Opus 5.5	$0.00213	$0.00213
Sonnet 5.5	$0.00106	$0.00106
Haiku 4.5	$0.00053	$0.00053

Measured 2mo ago against content hash b86598145f40, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentsitter 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 2mo 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 · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

md-analyzer

Purpose

Analyze, score, and optimize AI coding agent config files (CLAUDE.md, .cursorrules, .clinerules, CODEX.md, GEMINI.md, .windsurfrules, copilot-instructions.md). Works as an MCP tool.

Tech Stack

TypeScript + Node.js 22+
MCP SDK (@modelcontextprotocol/sdk)

Supported Platforms

Claude Code, Cursor, Cline, Codex, Gemini CLI, GitHub Copilot, Windsurf, Amp, Antigravity, OpenCode, Kimi Code CLI, Warp, Firebender

Analysis Criteria

Token cost estimation (file size → estimated tokens → per-session cost)
Vague rule detection ("write good content" style ambiguity)
Missing section check (variables, examples, do/don't rules)
Duplicate content detection
Attention placement (critical info at head/tail for LLM U-shaped attention)
Structure analysis (markdown heading usage, grouping)

Output Format

Overall score: 0-100
Category scores (clarity, structure, token efficiency, coverage)
Issues list (severity: critical/warning/info)
Optimized version suggestion

Rules

All code, comments, and documentation in English
Write unit tests for every tool
Test before creating files

Skill routing

When the user's request matches an available skill, invoke it via the Skill tool. When in doubt, invoke the skill.

Key routing rules:

Product ideas/brainstorming → invoke /office-hours
Strategy/scope → invoke /plan-ceo-review
Architecture → invoke /plan-eng-review
Design system/plan review → invoke /design-consultation or /plan-design-review
Full review pipeline → invoke /autoplan
Bugs/errors → invoke /investigate
QA/testing site behavior → invoke /qa or /qa-only
Code review/diff check → invoke /review
Visual polish → invoke /design-review
Ship/deploy/PR → invoke /ship or /land-and-deploy
Save progress → invoke /context-save
Resume context → invoke /context-restore

Commands

npm run build       # compile TypeScript → dist/
npm run build:web   # bundle browser script → web/scoring/bundle.js
npm test            # run all 230 unit tests (vitest)
npm run dev         # run MCP server in dev mode (tsx)

Read the full file on GitHub · 60 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.

2mo ago First seen · 60 lines · 532 tokens per session scan A b86598145f40

Subscribe to this mod's changes

agentsitter CLAUDE.md is an instructions file published in the GitHub repository serdaraytac/agentsitter (8 stars, last pushed 5mo ago), licensed MIT. It adds 532 tokens to every session, about $0.0021 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 2026-08-31.

Building agents

agentsitter CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentsitter CLAUDE.mdserdaraytac/agentsitter	Instructions file	8	5mo ago	MIT	A	532	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
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
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	2d ago	MIT	A	4,313	Codex, OpenCode

agentsitter: Instructions file for Claude Code