What is synto CLAUDE.md?

A project instruction file for Synto, a Python application with local processing stages and optional language-model smoke tests. It lists installation, testing, formatting, and model-server commands.

It helps install dependencies, run focused or complete tests, measure coverage, format and lint Python code, and run model-backed smoke comparisons.

It gives agents the exact supported commands and explains which checks work offline versus which require a local LM Studio server.

How kytmanov/synto configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kytmanov/synto. 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/kytmanov/synto/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kytmanov/synto

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/kytmanov/synto/claude-md/github.svg)](https://agentmods.dev/instructions/kytmanov/synto/claude-md)

Your own site

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

Per session 1,388 This file is loaded in full into every session.

When invoked 1,388 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	$0.01388	$0.01388
Opus 5.5	$0.00555	$0.00555
Sonnet 5.5	$0.00278	$0.00278
Haiku 4.5	$0.00139	$0.00139

Measured 2mo ago against content hash e17c260e992f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

synto 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 · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 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.

Commands

# Install (editable, auto-detects uv/pip)
python install.py

# Dependencies
uv sync --group dev

# Tests (all offline, no Ollama required)
uv run pytest
uv run pytest tests/test_ingest.py::test_function_name -v   # single test
uv run pytest --cov=src/synto                   # with coverage

# Lint & format
uv run ruff check src/ tests/
uv run ruff format --check src/ tests/
uv run ruff format src/ tests/        # auto-fix

# Smoke tests (user preference: run against LM Studio with gemma4:e4b)
# Requires LM Studio server at http://localhost:1234/v1 with gemma4:e4b loaded.
PROVIDER=lm_studio FAST_MODEL=gemma4:e4b HEAVY_MODEL=gemma4:e4b bash scripts/smoke_test.sh
PROVIDER=lm_studio FAST_MODEL=gemma4:e4b HEAVY_MODEL=gemma4:e4b bash scripts/compare_smoke.sh
# If LM Studio rejects the alias, use the exact loaded id it reports, e.g.
# PROVIDER=lm_studio FAST_MODEL=google/gemma-4-e4b HEAVY_MODEL=google/gemma-4-e4b bash scripts/smoke_test.sh
# The main smoke can take 15+ minutes with gemma4:e4b; use a long command timeout.

Architecture

Three-stage local LLM pipeline turning Obsidian raw notes into a synthesized wiki via Ollama.

Data flow: raw/*.md → ingest (fast model → AnalysisResult) → compile (heavy model → SingleArticle drafts) → approve (publish to wiki/)

Vault structure: raw/ (immutable user notes), wiki/ (published articles), wiki/.drafts/, wiki/sources/, wiki/queries/, wiki/synthesis/, .synto/state.db

Query synthesis

synto query --save writes dated Q&A notes to wiki/queries/
synto query --synthesize writes published synthesis articles to wiki/synthesis/
synthesis rows are tracked in wiki_articles with kind="synthesis", question_hash, synthesis_sources, and synthesis_source_hashes
duplicate syntheses are keyed by normalized question hash
update_in_place must respect manual-edit protection by comparing the on-disk body hash with the DB content_hash
compare runs must not create or mutate active wiki/synthesis/ content

Read the full file on GitHub · 84 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 · 84 lines · 1,388 tokens per session scan A e17c260e992f

Subscribe to this mod's changes

synto CLAUDE.md is an instructions file published in the GitHub repository kytmanov/synto (266 stars, last pushed 29d ago), licensed MIT. It adds 1,388 tokens to every session, about $0.0056 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 2026-08-30.

git-based-wiki karpathy knowledge-base llm-knowledge-base llm-pipeline llm-tools

synto CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
synto CLAUDE.mdkytmanov/synto	Instructions file	266	29d ago	MIT	A	1,388	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	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	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

synto: Instructions file for Claude Code