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.
npx agentmods add instructions/jyunming/axon/testergit clone --depth 1 https://github.com/jyunming/AxonWrote 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/instructions/jyunming/axon/tester)<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>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 | $0.00709 | $0.00709 |
| Opus 5 | $0.00354 | $0.00354 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
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.
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
pytestfixtures for shared setup (e.g., a defaultAxonConfig, 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) — useunittest.mock.patch. - ChromaDB (
chromadb.PersistentClient) — mock the collection'saddandquerymethods. - SentenceTransformer — mock
encode()to return a fixed list of floats. - BM25 file I/O — use
tmp_pathpytest fixture forstorage_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.yamlis missing. query()returns a string; callsembed_query,vector_store.search,llm.complete.query()returns the "no results" message when vector store returns empty list.ingest()callsvector_store.addwith correctly structured ids/texts/embeddings.
loaders.py
TextLoader.load()returns correct document dict withid,text,metadata.JSONLoader.load()handles both list and dict JSON input.TSVLoader.load()usescontentcolumn if present, else first column.DirectoryLoader.load()skips unsupported file extensions silently.BMPLoader.load()returns[]whenollamais 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 /healthreturns{"status": "ok", "project": "<name>"}(200) when ready, or{"status": "initializing"}(503) when brain is not yet initialized.POST /queryreturns 503 when the globalbraininstance isNone.POST /add_textauto-generatesdoc_idwhen not provided.POST /ingestreturns 404 when path does not exist.
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.
- 3d ago First seen · 66 lines · 709 tokens per session scan A a62590af6c88
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.
Other instructions, from other repositories
OpenNotebookLM AGENTS.md
Instructions for tom1030507/OpenNotebookLM, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
knowledge-base CLAUDE.md
Claude Code instructions for riemannulus/knowledge-base, covering knowledge-base 개발 가이드, 명령어, 아키텍처 (데이터 흐름), 깨뜨리기 쉬운 불변 원칙 and 확장 포인트.
fortemi CLAUDE.md
Claude Code instructions for Fortemi/fortemi, covering matric memory, ci/cd, gitea actions workflows, monitoring builds and check recent runs via mcp.
fortemi AGENTS.md
AGENTS.md instructions for Fortemi/fortemi, covering agents.md, framework context, tier 1 / tier 2 / tier 3 loading model, tier 2 capability map and agents.
RAG-In-A-Box AGENTS.md
AGENTS.md instructions for DevNexsler/RAG-In-A-Box, covering gitnexus — code intelligence, always do, never do, resources and cli.
RAG-In-A-Box CLAUDE.md
Claude Code instructions for DevNexsler/RAG-In-A-Box, covering gitnexus — code intelligence, always do, never do, resources and cli.