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.
curl -O https://raw.githubusercontent.com/anam-org/metaxy/main/.claude/skills/sybil/SKILL.mdgit clone --depth 1 https://github.com/anam-org/metaxyWrote 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/skills/anam-org/metaxy/sybil)<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>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 | $0.00030 | $0.01419 |
| Opus 5 | $0.00015 | $0.00709 |
| Sonnet 5 | $0.00006 | $0.00284 |
| Haiku 4.5 | $0.00003 | $0.00142 |
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.
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.pyfile as module, names available in namespacePythonDocStringDocument: Parse only docstrings from.pyfiles
from sybil.document import PythonDocStringDocument
pytest_collect_file = Sybil(
parsers=[...],
patterns=["src/**/*.py"],
document_types={".py": PythonDocStringDocument},
).pytest()
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.
- 5d ago First seen · 249 lines · 30 tokens per session scan A bc0d0c5591e5
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.
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.
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.
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.
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.
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".
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…