metaxy: Skill for Claude Code

.claude/skills/sybil/SKILL.md

sybil is a skill for Claude Code from anam-org/metaxy. It costs 30 tokens per session (1,419 once invoked), scanned A, original, Apache-2.0.

A testing setup for code examples embedded in documentation and docstrings. It parses those examples and runs them as part of the normal test suite.

In plain words
What is it for?
Use it with pytest to execute Python examples in Markdown files or Python source, configure parsers and file patterns, skip selected examples, and share test fixtures.
Why use it?
It helps catch documentation examples that no longer work, so instructions do not quietly drift away from the code.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is anam-org/metaxy's own configuration. It tells Claude Code how to work on metaxy 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 metaxy configures →

Part of the metaxy plugin — 8 skills, 5 agents, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to anam-org/metaxy. 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/anam-org/metaxy/main/.claude/skills/sybil/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/anam-org/metaxy

Made for: Claude Code.

Or install metaxy, the plugin that ships this one along with the rest of its 8 skills, 5 agents, 1 hook.

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 sybil

README.md
[![agentmods](https://agentmods.dev/badge/skills/anam-org/metaxy/sybil.svg)](https://agentmods.dev/skills/anam-org/metaxy/sybil)
Your own site
<a href="https://agentmods.dev/skills/anam-org/metaxy/sybil"><img src="https://agentmods.dev/badge/skills/anam-org/metaxy/sybil.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,419 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01419
Opus 5 $0.00015 $0.00709
Sonnet 5 $0.00006 $0.00284
Haiku 4.5 $0.00003 $0.00142

Measured 5d ago against content hash bc0d0c5591e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

sybil 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 5d 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/skills/sybil/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sybil Documentation Testing

Sybil validates code examples embedded in documentation and docstrings by parsing and executing them as part of normal test runs.

Official Documentation: https://sybil.readthedocs.io/en/latest/

Installation

pip install sybil[pytest]

Pytest Integration

Configure in conftest.py. See pytest integration docs.

from sybil import Sybil
from sybil.parsers.markdown.codeblock import PythonCodeBlockParser
from sybil.parsers.markdown.skip import SkipParser

pytest_collect_file = Sybil(
    parsers=[
        SkipParser(),
        PythonCodeBlockParser(),
    ],
    patterns=["*.md", "**/*.py"],
).pytest()

Sybil Parameters

See API reference.

Parameter Description
parsers Sequence of parser callables
patterns File glob patterns to include (e.g., ["*.md", "src/**/*.py"])
excludes File glob patterns to exclude
setup Callable receiving namespace dict, called before each document
teardown Callable receiving namespace dict, called after each document
fixtures List of pytest fixture names to inject into namespace
document_types Map file extensions to Document classes

Document Types

See API reference.

  • Default: Parse entire file
  • PythonDocument: Import .py file as module, names available in namespace
  • PythonDocStringDocument: Parse only docstrings from .py files
from sybil.document import PythonDocStringDocument

pytest_collect_file = Sybil(
    parsers=[...],
    patterns=["src/**/*.py"],
    document_types={".py": PythonDocStringDocument},
).pytest()

Read the full file on GitHub · 249 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. 5d ago First seen · 249 lines · 30 tokens per session scan A bc0d0c5591e5

Subscribe to this mod's changes

sybil is a skill published in the GitHub repository anam-org/metaxy (119 stars, last pushed 16d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,419 once invoked, about $0.0002 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 2026-09-01.

Related

Other skills, from other repositories

test-review

You are an expert DataHub test reviewer. Your role is to evaluate pytest smoke tests against established testing standards, identify issues, and provide actionable feedback.

datahub-project/datahub · 0 tokens

animation-test-migration

Migrate a series type from ratio-snapshot animation tests and manual -test docs pages to frame-trajectory coverage. Use when converting a series (area, pie, scatter, histogram, range-bar, candlestick, radar, …) to the trajectory harness.

ag-grid/ag-charts · 57 tokens

chart-defaults

Find the actual runtime default value of any AG Charts configuration option, and keep JSDoc Default: markers accurate. Use when documenting a default, verifying a change has not altered one, writing tests against default behaviour, or auditing whether a TypeScript comment matches the theme template.

ag-grid/ag-charts · 60 tokens

mock-data-generator

A tool that creates realistic sample data from a schema or type definition. Sample data is made-up information used while building or testing software.

chainlesschain/chainlesschain · 19 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

migrate-xunit-to-xunit-v3

Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…

dotnet/skills · 149 tokens