open-kgo: Instructions file for Claude Code

CLAUDE.md

open-kgo CLAUDE.md is an instructions file for Claude Code from mloda-ai/open-kgo. It costs 1,350 tokens per session, scanned A, a copy of open-kgo AGENTS.md, Apache-2.0.

A repository guide for open-kgo, a Python project built with the mloda framework. It defines the setup steps, required checks, and commit-message format.

In plain words
What is it for?
Use it when changing open-kgo to install dependencies, run the full tox test suite, perform individual checks, or write compliant commits.
Why use it?
It tells the coding agent how to prepare the environment and what verification is required before considering changes finished.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is mloda-ai/open-kgo's own configuration. It tells Claude Code how to work on open-kgo 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 open-kgo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mloda-ai/open-kgo. 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/mloda-ai/open-kgo/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mloda-ai/open-kgo

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 open-kgo CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mloda-ai/open-kgo/claude-md"><img src="https://agentmods.dev/badge/instructions/mloda-ai/open-kgo/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,350 This file is loaded in full into every session.
When invoked 1,350 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 100% copy Near-identical to another mod 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 $0.01350 $0.01350
Opus 5 $0.00675 $0.00675
Sonnet 5 $0.00270 $0.00270
Haiku 4.5 $0.00135 $0.00135

Measured yesterday against content hash ce56837b3725, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

open-kgo 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 yesterday.

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.

Origin

This is a copy

100% identical to open-kgo AGENTS.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Must read README.md first.

This project uses the mloda framework. Assume any given task is related to mloda.

Environment

source .venv/bin/activate

Dependencies

Use uv to install dependencies:

uv sync --all-extras

Running checks

Use tox to run all checks:

tox

Run checks from the project virtualenv:

source .venv/bin/activate && tox

tox is the required final verification step after code or dependency changes. Running only pytest is not sufficient for completion.

Run individual checks

pytest
ruff format --check --line-length 120 .
ruff check .
mypy --strict --ignore-missing-imports .
bandit -c pyproject.toml -r -q .

Commit messages

Use Conventional Commit format for all commits so semantic versioning/release tooling can parse intent. Do not include Co-Authored-By lines or any other mention of AI agents in commit messages.

Examples:

  • fix: handle empty feature set
  • chore(deps): bump mloda to 0.4.6

Claude Code Skills

The mloda-registry provides Claude Code skills that assist with plugin development:

When helping with FeatureGroups, ComputeFrameworks, or Extenders, leverage these skills for pattern guidance and best practices.

Project Practices

tox is the gate. It runs pytest, then ruff format --check, ruff check, mypy --strict --ignore-missing-imports, and bandit. All of these must pass before a PR is mergeable. CVE scanning lives in a separate tox -e security environment that runs pip-audit; it is not part of the PR merge gate. Scheduled CVE scanning is left to GitHub's native Dependabot security alerts, with tox -e security available for on-demand local scans.

  • Python: supported range is >=3.10. The default tox env is python310.
  • Type hints: use modern forms (list[str], dict[str, int], X | None).
  • Formatting: ruff format with line length 120.
  • Linting: [tool.ruff.lint] select is pinned to ruff's pre-0.16 default rule set (E4, E7, E9, F); ruff 0.16 broadened its defaults from 59 to 413 rules, and adopting that larger set is a separate, deliberate decision, not something a routine dependency bump should silently pull in.
  • Tests: every new feature or bug fix must come with tests; follow the patterns in the existing open_kgo/.../tests/ trees.
  • Test contract harness (in-repo, not a published library): KG connectors are tested via a shared, inherited contract suite, the same pattern mloda-registry uses, but it currently lives inside this repo and is not packaged or published for external reuse (unlike mloda-registry's separate mloda-testing package). Structure: a universal KgConnectorContractBase in open_kgo/feature_groups/kg/tests/kg_contract.py, a per-family <Family>ContractTestBase in each open_kgo/feature_groups/kg/<family>/tests/kg_<family>_contract.py, the shared run_query/make_valid_credentials helpers in open_kgo/feature_groups/kg/tests/_helpers.py (reader discovery in _discovery.py), and the resource-cache loaders in the production module open_kgo/feature_groups/kg/fixtures.py (caches cleared per-test by open_kgo/feature_groups/kg/conftest.py). A holistic all-family smoke plus cross-family gap diagnostics live in open_kgo/feature_groups/kg/tests/test_kg_usage_smoke.py, test_kg_registry_integrity.py, and test_kg_catalog_declarations.py, all over the shared _family_cases.py registry. Each concrete plugin's test class subclasses its family base and supplies a few small adapter methods. When adding a connector, extend the existing family base rather than writing standalone tests. Note also that, unlike mloda-registry, there is no framework-adapter-mixin layer and no single canonical fixture dataset.
  • Supply chain: [tool.uv] exclude-newer = "7 days" in pyproject.toml defers new third-party dependency releases by 7 days; exclude-newer-package exempts the first-party mloda and mloda-testing packages from that cooldown (rolling "0 days"; mloda-registry is a third reserved entry, not yet an actual dependency), so mloda and mloda-testing releases are picked up immediately. override-dependencies pins two packages past what their own constraints allow: pymdown-extensions>=11.0.1 past marimo's <11 pin, because the fix for the b64 path-traversal advisory only ships in 11.0 and a constraint cannot beat an upper pin; and mloda>=0.12.0,<0.13.0, capping the floor so a breaking next-minor release isn't picked up automatically. Do not edit these without a reason.
  • Commits: use Conventional Commits (feat:, fix:, chore:, docs:, test:, refactor:, style:, ci:, build:, perf:). semantic-release computes the next version: feat: triggers a minor bump, all other types trigger a patch bump (see .releaserc.yaml).

Read the full file on GitHub · 85 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. yesterday Changed · +1 lines · +85 tokens per session ce56837b3725
  2. 9d ago First seen · 84 lines · 1,265 tokens per session scan A c04750c9a8d1

Subscribe to this mod's changes

open-kgo CLAUDE.md is an instructions file published in the GitHub repository mloda-ai/open-kgo (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,350 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to open-kgo AGENTS.md, differing in 2 lines, and is treated as a copy.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens