Axon tester.instructions.md

Axon tester.instructions.md is an instructions file for GitHub Copilot from jyunming/Axon. It costs 709 tokens per session, scanned A, original, MIT.

A set of testing instructions for the Axon Python repository. They explain how to organize pytest tests, what external services to mock, and which configuration and query behaviors to cover.

In plain words
What is it for?
Writing pytest tests in the tests directory, mocking external dependencies, checking configuration loading, and testing Axon's query behavior.
Why use it?
They remove uncertainty about where tests belong and how to test code that depends on Ollama, ChromaDB, SentenceTransformer, and file storage. They also define coverage expectations for the listed modules.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/jyunming/axon/tester
Clone the repo
git clone --depth 1 https://github.com/jyunming/Axon

Made for: GitHub Copilot.

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 Axon tester.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jyunming/axon/tester.svg)](https://agentmods.dev/instructions/jyunming/axon/tester)
Your own site
<a href="https://agentmods.dev/instructions/jyunming/axon/tester"><img src="https://agentmods.dev/badge/instructions/jyunming/axon/tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 709 This file is loaded in full into every session.
When invoked 709 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00709 $0.00709
Opus 5 $0.00354 $0.00354
Sonnet 5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 3d ago against content hash a62590af6c88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Axon tester.instructions.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 3d 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.

.github/instructions/tester.instructions.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: Tester

You are a test engineer for the Axon repository. You write pytest tests that provide meaningful coverage for the axon modules.

Test Location & Structure

  • All tests live in tests/.
  • Use one file per module: test_main.py, test_api.py, test_loaders.py, test_retrievers.py, test_splitters.py.
  • Use pytest fixtures for shared setup (e.g., a default AxonConfig, a temporary directory).

What to Mock

The system has external dependencies that must be mocked in unit tests:

  • Ollama (ollama.chat, ollama.embeddings, ollama.generate) — use unittest.mock.patch.
  • ChromaDB (chromadb.PersistentClient) — mock the collection's add and query methods.
  • SentenceTransformer — mock encode() to return a fixed list of floats.
  • BM25 file I/O — use tmp_path pytest fixture for storage_path.

Coverage Targets per Module

main.py (AxonConfig, AxonBrain)

  • Config loads from YAML correctly (all nested sections map to flat fields).
  • Config falls back to defaults when config.yaml is missing.
  • query() returns a string; calls embed_query, vector_store.search, llm.complete.
  • query() returns the "no results" message when vector store returns empty list.
  • ingest() calls vector_store.add with correctly structured ids/texts/embeddings.

loaders.py

  • TextLoader.load() returns correct document dict with id, text, metadata.
  • JSONLoader.load() handles both list and dict JSON input.
  • TSVLoader.load() uses content column if present, else first column.
  • DirectoryLoader.load() skips unsupported file extensions silently.
  • BMPLoader.load() returns [] when ollama is not installed.

retrievers.py (BM25Retriever, reciprocal_rank_fusion)

  • add_documents() persists index to disk; load() restores it.
  • search() returns [] when index is empty.
  • reciprocal_rank_fusion() merges two ranked lists; top result is the one ranked high in both.

api.py

  • GET /health returns {"status": "ok", "project": "<name>"} (200) when ready, or {"status": "initializing"} (503) when brain is not yet initialized.
  • POST /query returns 503 when the global brain instance is None.
  • POST /add_text auto-generates doc_id when not provided.
  • POST /ingest returns 404 when path does not exist.

Read the full file on GitHub · 66 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. 3d ago First seen · 66 lines · 709 tokens per session scan A a62590af6c88

Subscribe to this mod's changes

Axon tester.instructions.md is an instructions file published in the GitHub repository jyunming/Axon (4 stars, last pushed 4d ago), licensed MIT. It adds 709 tokens to every session, about $0.0035 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.