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.
npx agentmods add instructions/mrosata/codetex-mcp/claude-mdgit clone --depth 1 https://github.com/mrosata/codetex-mcpWrote 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.
[](https://agentmods.dev/instructions/mrosata/codetex-mcp/claude-md)<a href="https://agentmods.dev/instructions/mrosata/codetex-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mrosata/codetex-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00956 | $0.00956 |
| Opus 5 | $0.00478 | $0.00478 |
| Sonnet 5 | $0.00191 | $0.00191 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
codetex-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
codetex-mcp is a commit-aware code context manager for LLMs, providing both an MCP server (stdio transport) and a CLI. It indexes Git repositories into a multi-tier context hierarchy (repo overview → file summaries → symbol details), stores results in SQLite with sqlite-vec for vector search, and serves them to LLM clients via the MCP protocol.
Status: Early stage — project scaffolding and detailed architecture/PRD exist, implementation is in progress.
Development Environment
- Python: >=3.12 (see
.python-version) - Package Manager: uv
- Linting/Formatting: ruff
- Type Checking: mypy
- Testing: pytest with pytest-asyncio
Commands
# Install dependencies
uv sync
# Run tests
uv run pytest
# Run a single test file
uv run pytest tests/test_storage/test_database.py
# Run tests with coverage
uv run pytest --cov=codetex_mcp
# Lint and format
uv run ruff check src/ tests/
uv run ruff format src/ tests/
# Type check
uv run mypy src/
# Run CLI
uv run codetex <command>
# Run as module
uv run python -m codetex_mcp
# Run MCP server (stdio transport)
uv run codetex serve
Architecture
Two entry points (CLI via Typer, MCP server via FastMCP) share the same core service layer. No DI framework — services are wired manually via a create_app() factory.
CLI (typer) ──┐
├──▶ core/ (RepoManager, Indexer, Syncer, ContextStore, SearchEngine)
MCP (FastMCP)─┘ │ │ │
analysis/ llm/ embeddings/
(tree-sitter + fallback) (sentence-transformers)
└──────────┼────────────┘
storage/ (SQLite + sqlite-vec)
│
git/ ←─┴──▶ config/
Key modules under src/codetex_mcp/:
cli/app.py— Typer app with 8 commands (add, index, sync, context, status, list, serve, config)server/mcp_server.py— FastMCP server with 7 toolscore/— Domain logic (no direct I/O, dependencies injected)analysis/— Tree-sitter AST parsing with regex fallback;parser.pyis the unified dispatcherllm/provider.py— Abstract base + Anthropic implementation for tier summarizationembeddings/embedder.py— sentence-transformers wrapper (lazy model loading)storage/— SQLite via aiosqlite; DAO pattern with separate modules per entity (repositories, files, symbols, vectors)storage/migrations/— SQL migration files applied bydatabase.pygit/operations.py— Subprocess git wrapper (no GitPython)config/settings.py— TOML config loader with env var overridesexceptions.py— Error hierarchy (11 exception classes)
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.
- 4d ago First seen · 97 lines · 956 tokens per session scan A 24b767ddb0c4
codetex-mcp CLAUDE.md is an instructions file published in the GitHub repository mrosata/codetex-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 956 tokens to every session, about $0.0048 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.